modelId
stringlengths 5
139
| author
stringlengths 2
42
| last_modified
timestamp[us, tz=UTC]date 2020-02-15 11:33:14
2025-09-13 18:26:42
| downloads
int64 0
223M
| likes
int64 0
11.7k
| library_name
stringclasses 558
values | tags
listlengths 1
4.05k
| pipeline_tag
stringclasses 55
values | createdAt
timestamp[us, tz=UTC]date 2022-03-02 23:29:04
2025-09-13 18:25:20
| card
stringlengths 11
1.01M
|
|---|---|---|---|---|---|---|---|---|---|
Azurastar2903/Llama-3.2-1B-Instruct-rk3588-1.2.1
|
Azurastar2903
| 2025-08-19T13:08:41Z | 0 | 0 |
transformers
|
[
"transformers",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"license:llama3.2",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T13:07:43Z |
---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
license: llama3.2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version\
\ Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions\
\ for use, reproduction, distribution and modification of the Llama Materials set\
\ forth herein.\n\n“Documentation” means the specifications, manuals and documentation\
\ accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\
\n“Licensee” or “you” means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf),\
\ of the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2”\
\ means the foundational large language models and software and algorithms, including\
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
\ by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means,\
\ collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion\
\ thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms\
\ Ireland Limited (if you are located in or, if you are an entity, your principal\
\ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if\
\ you are located outside of the EEA or Switzerland). \n\nBy clicking “I Accept”\
\ below or by using or distributing any portion or element of the Llama Materials,\
\ you agree to be bound by this Agreement.\n\n1. License Rights and Redistribution.\n\
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
\ and royalty-free limited license under Meta’s intellectual property or other rights\
\ owned by Meta embodied in the Llama Materials to use, reproduce, distribute,\
\ copy, create derivative works of, and make modifications to the Llama Materials.\
\ \nb. Redistribution and Use. \ni. If you distribute or make available the Llama\
\ Materials (or any derivative works thereof), or a product or service (including\
\ another AI model) that contains any of them, you shall (A) provide a copy of this\
\ Agreement with any such Llama Materials; and (B) prominently display “Built with\
\ Llama” on a related website, user interface, blogpost, about page, or product\
\ documentation. If you use the Llama Materials or any outputs or results of the\
\ Llama Materials to create, train, fine tune, or otherwise improve an AI model,\
\ which is distributed or made available, you shall also include “Llama” at the\
\ beginning of any such AI model name.\nii. If you receive Llama Materials, or any\
\ derivative works thereof, from a Licensee as part of an integrated end user product,\
\ then Section 2 of this Agreement will not apply to you. \niii. You must retain\
\ in all copies of the Llama Materials that you distribute the following attribution\
\ notice within a “Notice” text file distributed as a part of such copies: “Llama\
\ 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2\
\ version release date, the monthly active users of the products or services made\
\ available by or for Licensee, or Licensee’s affiliates, is greater than 700 million\
\ monthly active users in the preceding calendar month, you must request a license\
\ from Meta, which Meta may grant to you in its sole discretion, and you are not\
\ authorized to exercise any of the rights under this Agreement unless or until\
\ Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS\
\ REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM\
\ ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\
\ ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION,\
\ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR\
\ PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING\
\ OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR\
\ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability.\
\ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\
\ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\
\ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\
\ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\
\ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\n\
a. No trademark licenses are granted under this Agreement, and in connection with\
\ the Llama Materials, neither Meta nor Licensee may use any name or mark owned\
\ by or associated with the other or any of its affiliates, except as required\
\ for reasonable and customary use in describing and redistributing the Llama Materials\
\ or as set forth in this Section 5(a). Meta hereby grants you a license to use\
\ “Llama” (the “Mark”) solely as required to comply with the last sentence of Section\
\ 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at\
\ https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising\
\ out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to\
\ Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\
\ respect to any derivative works and modifications of the Llama Materials that\
\ are made by you, as between you and Meta, you are and will be the owner of such\
\ derivative works and modifications.\nc. If you institute litigation or other proceedings\
\ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)\
\ alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion\
\ of any of the foregoing, constitutes infringement of intellectual property or\
\ other rights owned or licensable by you, then any licenses granted to you under\
\ this Agreement shall terminate as of the date such litigation or claim is filed\
\ or instituted. You will indemnify and hold harmless Meta from and against any\
\ claim by any third party arising out of or related to your use or distribution\
\ of the Llama Materials.\n6. Term and Termination. The term of this Agreement will\
\ commence upon your acceptance of this Agreement or access to the Llama Materials\
\ and will continue in full force and effect until terminated in accordance with\
\ the terms and conditions herein. Meta may terminate this Agreement if you are\
\ in breach of any term or condition of this Agreement. Upon termination of this\
\ Agreement, you shall delete and cease use of the Llama Materials. Sections 3,\
\ 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and\
\ Jurisdiction. This Agreement will be governed and construed under the laws of\
\ the State of California without regard to choice of law principles, and the UN\
\ Convention on Contracts for the International Sale of Goods does not apply to\
\ this Agreement. The courts of California shall have exclusive jurisdiction of\
\ any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\n\
Meta is committed to promoting safe and fair use of its tools and features, including\
\ Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy\
\ (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\n\
#### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly.\
\ You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 1. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 3.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 4. Collect, process, disclose, generate, or infer private or sensitive\
\ information about individuals, including information about individuals’ identity,\
\ health, or demographic information, unless you have obtained the right to do so\
\ in accordance with applicable law\n 5. Engage in or facilitate any action or\
\ generate any content that infringes, misappropriates, or otherwise violates any\
\ third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 6. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n 7. Engage in any action, or\
\ facilitate any action, to intentionally circumvent or remove usage restrictions\
\ or other safety measures, or to enable functionality disabled by Meta \n2. Engage\
\ in, promote, incite, facilitate, or assist in the planning or development of activities\
\ that present a risk of death or bodily harm to individuals, including use of Llama\
\ 3.2 related to the following:\n 8. Military, warfare, nuclear industries or\
\ applications, espionage, use for materials or activities that are subject to the\
\ International Traffic Arms Regulations (ITAR) maintained by the United States\
\ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989\
\ or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and\
\ illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled\
\ substances\n 11. Operation of critical infrastructure, transportation technologies,\
\ or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting,\
\ and eating disorders\n 13. Any content intended to incite or promote violence,\
\ abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive\
\ or mislead others, including use of Llama 3.2 related to the following:\n 14.\
\ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\
\ 15. Generating, promoting, or furthering defamatory content, including the\
\ creation of defamatory statements, images, or other content\n 16. Generating,\
\ promoting, or further distributing spam\n 17. Impersonating another individual\
\ without consent, authorization, or legal right\n 18. Representing that the\
\ use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating\
\ false online engagement, including fake reviews and other means of fake online\
\ engagement \n4. Fail to appropriately disclose to end users any known dangers\
\ of your AI system 5. Interact with third party tools, models, or software designed\
\ to generate unlawful content or engage in unlawful or harmful conduct and/or represent\
\ that the outputs of such tools, models, or software are associated with Meta or\
\ Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the\
\ rights granted under Section 1(a) of the Llama 3.2 Community License Agreement\
\ are not being granted to you if you are an individual domiciled in, or a company\
\ with a principal place of business in, the European Union. This restriction does\
\ not apply to end users of a product or service that incorporates any such multimodal\
\ models.\n\nPlease report any violation of this Policy, software “bug,” or other\
\ problems that could lead to a violation of this Policy through one of the following\
\ means:\n\n* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\n\
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n\
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama\
\ 3.2: LlamaUseReport@meta.com"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
# Llama-3.2-1B-Instruct-RK3588-1.2.1
This version of Llama-3.2-1B-Instruct has been converted to run on the RK3588 NPU using ['w8a8', 'w8a8_g128', 'w8a8_g256'] quantization.
This model has been optimized with the following LoRA:
Compatible with RKLLM version: 1.2.1
## Useful links:
[Official RKLLM GitHub](https://github.com/airockchip/rknn-llm)
[RockhipNPU Reddit](https://reddit.com/r/RockchipNPU)
[EZRKNN-LLM](https://github.com/Pelochus/ezrknn-llm/)
Pretty much anything by these folks: [marty1885](https://github.com/marty1885) and [happyme531](https://huggingface.co/happyme531)
Converted using https://github.com/c0zaut/ez-er-rkllm-toolkit
# Original Model Card for base model, Llama-3.2-1B-Instruct, below:
## Model Information
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
**Model Developer:** Meta
**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
| | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2 (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
| Llama 3.2 Quantized (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 8k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-1B-Instruct, for use with transformers and with the original `llama` codebase.
### Use with transformers
Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
Make sure to update your transformers installation via `pip install --upgrade transformers`.
```python
import torch
from transformers import pipeline
model_id = "meta-llama/Llama-3.2-1B-Instruct"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```
Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Llama-3.2-1B-Instruct --include "original/*" --local-dir Llama-3.2-1B-Instruct
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | ----- | :---: | :---: | :---: |
| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
| Llama 3.2 1B SpinQuant | 1.7 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 3B SpinQuant | 2.4 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 1B QLora | 1.3k | 0 | 700 | 0.381 | 0 |
| Llama 3.2 3B QLora | 1.6k | 0 | 700 | 0.461 | 0 |
| Total | 833k | 86k | | 240 | 0 |
\*\* The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required.
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Quantization
### Quantization Scheme
We designed the current quantization scheme with the [PyTorch’s ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts:
- All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations.
- The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation.
- Similar to classification layer, an 8-bit per channel quantization is used for embedding layer.
### Quantization-Aware Training and LoRA
The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO).
### SpinQuant
[SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length.
## Benchmarks \- English Text
In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
| | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
| | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
| | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
| | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
### Instruction Tuned Models
| Capability | | Benchmark | \# Shots | Metric | Llama 3.2 1B bf16 | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B bf16 | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | | MMLU | 5 | macro\_avg/acc | 49.3 | 43.3 | 47.3 | 49.0 | 63.4 | 60.5 | 62 | 62.4 | 69.4 |
| Re-writing | | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 39.2 | 40.9 | 41.2 | 40.1 | 40.3 | 40.8 | 40.7 | 40.9 |
| Summarization | | TLDR9+ (test) | 1 | rougeL | 16.8 | 14.9 | 16.7 | 16.8 | 19.0 | 19.1 | 19.2 | 19.1 | 17.2 |
| Instruction following | | IFEval | 0 | Avg(Prompt/Instruction acc Loose/Strict) | 59.5 | 51.5 | 58.4 | 55.6 | 77.4 | 73.9 | 73.5 | 75.9 | 80.4 |
| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |
| | | MATH (CoT) | 0 | final\_em | 30.6 | 20.5 | 25.3 | 31.0 | 48.0 | 44.2 | 45.3 | 49.2 | 51.9 |
| Reasoning | | ARC-C | 0 | acc | 59.4 | 54.3 | 57 | 60.7 | 78.6 | 75.6 | 77.6 | 77.6 | 83.4 |
| | | GPQA | 0 | acc | 27.2 | 25.9 | 26.3 | 25.9 | 32.8 | 32.8 | 31.7 | 33.9 | 32.8 |
| | | Hellaswag | 0 | acc | 41.2 | 38.1 | 41.3 | 41.5 | 69.8 | 66.3 | 68 | 66.3 | 78.7 |
| Tool Use | | BFCL V2 | 0 | acc | 25.7 | 14.3 | 15.9 | 23.7 | 67.0 | 53.4 | 60.1 | 63.5 | 67.1 |
| | | Nexus | 0 | macro\_avg/acc | 13.5 | 5.2 | 9.6 | 12.5 | 34.3 | 32.4 | 31.5 | 30.1 | 38.5 |
| Long Context | | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | N/A | N/A | N/A | 19.8 | N/A | N/A | N/A | 27.3 |
| | | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | N/A | N/A | N/A | 63.3 | N/A | N/A | N/A | 72.2 |
| | | NIH/Multi-needle | 0 | recall | 75.0 | N/A | N/A | N/A | 84.7 | N/A | N/A | N/A | 98.8 |
| Multilingual | | MGSM (CoT) | 0 | em | 24.5 | 13.7 | 18.2 | 24.4 | 58.2 | 48.9 | 54.3 | 56.8 | 68.9 |
\*\*for comparison purposes only. Model not released.
### Multilingual Benchmarks
| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | MMLU (5-shot, macro_avg/acc) | Portuguese | 39.8 | 34.9 | 38.9 | 40.2 | 54.5 | 50.9 | 53.3 | 53.4 | 62.1 |
| | | Spanish | 41.5 | 36.0 | 39.8 | 41.8 | 55.1 | 51.9 | 53.6 | 53.6 | 62.5 |
| | | Italian | 39.8 | 34.9 | 38.1 | 40.6 | 53.8 | 49.9 | 52.1 | 51.7 | 61.6 |
| | | German | 39.2 | 34.9 | 37.5 | 39.6 | 53.3 | 50.0 | 52.2 | 51.3 | 60.6 |
| | | French | 40.5 | 34.8 | 39.2 | 40.8 | 54.6 | 51.2 | 53.3 | 53.3 | 62.3 |
| | | Hindi | 33.5 | 30.0 | 32.1 | 34.0 | 43.3 | 40.4 | 42.0 | 42.1 | 50.9 |
| | | Thai | 34.7 | 31.2 | 32.4 | 34.9 | 44.5 | 41.3 | 44.0 | 42.2 | 50.3 |
\*\*for comparison purposes only. Model not released.
## Inference time
In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device.
| Category | Decode (tokens/sec) | Time-to-first-token (sec) | Prefill (tokens/sec) | Model size (PTE file size in MB) | Memory size (RSS in MB) |
| :---- | ----- | ----- | ----- | ----- | ----- |
| 1B BF16 (baseline) | 19.2 | 1.0 | 60.3 | 2358 | 3,185 |
| 1B SpinQuant | 50.2 (2.6x) | 0.3 (-76.9%) | 260.5 (4.3x) | 1083 (-54.1%) | 1,921 (-39.7%) |
| 1B QLoRA | 45.8 (2.4x) | 0.3 (-76.0%) | 252.0 (4.2x) | 1127 (-52.2%) | 2,255 (-29.2%) |
| 3B BF16 (baseline) | 7.6 | 3.0 | 21.2 | 6129 | 7,419 |
| 3B SpinQuant | 19.7 (2.6x) | 0.7 (-76.4%) | 89.7 (4.2x) | 2435 (-60.3%) | 3,726 (-49.8%) |
| 3B QLoRA | 18.5 (2.4x) | 0.7 (-76.1%) | 88.8 (4.2x) | 2529 (-58.7%) | 4,060 (-45.3%) |
(\*) The performance measurement is done using an adb binary-based approach.
(\*\*) It is measured on an Android OnePlus 12 device.
(\*\*\*) Time-to-first-token (TTFT) is measured with prompt length=64
*Footnote:*
- *Decode (tokens/second) is for how quickly it keeps generating. Higher is better.*
- *Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better.*
- *Prefill is the inverse of TTFT (aka 1/TTFT) in tokens/second. Higher is better*
- *Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch*
- *RSS size \- Memory usage in resident set size (RSS)*
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
3. Provide protections for the community to help prevent the misuse of our models
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
|
lilTAT/blockassist-bc-gentle_rugged_hare_1755608110
|
lilTAT
| 2025-08-19T12:55:37Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gentle rugged hare",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T12:55:34Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gentle rugged hare
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
BjarneNPO/finetune_19_08_2025_12_45_15
|
BjarneNPO
| 2025-08-19T12:55:30Z | 0 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"xlm-roberta",
"sentence-similarity",
"feature-extraction",
"dense",
"generated_from_trainer",
"dataset_size:19964",
"loss:MultipleNegativesRankingLoss",
"dataset:NPOA/Bjarne-Bachelorarbeit",
"arxiv:1908.10084",
"arxiv:1705.00652",
"base_model:FacebookAI/xlm-roberta-large",
"base_model:finetune:FacebookAI/xlm-roberta-large",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2025-08-19T12:55:12Z |
---
tags:
- sentence-transformers
- sentence-similarity
- feature-extraction
- dense
- generated_from_trainer
- dataset_size:19964
- loss:MultipleNegativesRankingLoss
base_model: FacebookAI/xlm-roberta-large
widget:
- source_sentence: bei einem kann keine hinterlegt werden
sentences:
- An einem Tag gab es im August eine Überbelegung, einmal erklärt wie sie diese
nachvollziehen kann.
- Fehlermeldung weist auf eine fehlende BI hin. Anwenderin stimmt sich dazu mit
ab.
- "Ticket\r\n---------------------------\r\nExport angepasst - informiert\r\n--------------------------\r\
\nUser möchte auch in der übergreifenden Personalliste die Anpassung umgesetzt\
\ haben - daher Ticket erneut geöffnet\r\n- übergreifender Export ebenfalls angepasst\
\ - informiert"
- source_sentence: Userin darf erst am 01.02.2024 die Vertragsangebote rausschicken,
möchte aber schonmal vermerken, welchen Kindern sie ein Vertragsangebot schicken
möchte.
sentences:
- Das ist noch nicht freigeschaltet. Genauer Zeitpunkt steht auch noch nicht fest.
- "Kind muss manuell angelegt werden und dann neu synchronisiert und Anmeldedaten\
\ zusammenführen.\r\nDa Userin weiterhin Anmeldedaten nicht zusammenführen kann\
\ Userin gebeten uns einen Screenshot aus dem Kita-Navigator zukommen zu lassen.\r\
\nBeide Kinder wurden nun übertragen und befinden sich unter Vetragsangeboten."
- Kann die Kinder auf die Planungsliste nehmen, dann sieht sie diese sowohl in der
Planungsliste, als auch in der Liste der Anmeldungen mit dem Symbol in der Anmeldeliste.
- source_sentence: Fehlermeldung beim Erstellen der Datei.
sentences:
- In der Benutzerverwaltung unter Verwaltung.
- Bei einer Kollegin musste noch die Stundenanzahl unter Ausbildung und Statistik
eingetragen werden.
- "Wurde an den Entwickler weitergegeben.\r\nProblem konnte behoben werden, Benutzer\
\ wurde informiert."
- source_sentence: möchte wissen wenn ein Kind gestern letzmalig in der Kita war,
welches Entlassdatum muss im System eingetragen werden?
sentences:
- Fehler bereist bekannt, prüft später erneut.
- Aktuell wurde uns noch nicht gemeldet, dass wir das Jugendamt freischalten sollen.
- Der letzte Betreuungstag muss als Entlassdatum hinterlegt werden, da sonst die
BI nicht stimmt.
- source_sentence: Login mit dem Authenticator funktioniert nicht mehr, Code ist immer
ungültig
sentences:
- Erneut die Tätigkeit gelöscht und neu Übertragen, die Tätigkeit wurde aber nicht
erneut angezeigt
- Nachdem die Uhrzeit neu synchronisiert war konnte sie sich wieder einloggen.
- Dies entspricht der Vorlage. muss Vorlage anpassen.
datasets:
- NPOA/Bjarne-Bachelorarbeit
pipeline_tag: sentence-similarity
library_name: sentence-transformers
---
# SentenceTransformer based on FacebookAI/xlm-roberta-large
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) on the [bjarne-bachelorarbeit](https://huggingface.co/datasets/NPOA/Bjarne-Bachelorarbeit) dataset. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
## Model Details
### Model Description
- **Model Type:** Sentence Transformer
- **Base model:** [FacebookAI/xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) <!-- at revision c23d21b0620b635a76227c604d44e43a9f0ee389 -->
- **Maximum Sequence Length:** 512 tokens
- **Output Dimensionality:** 1024 dimensions
- **Similarity Function:** Cosine Similarity
- **Training Dataset:**
- [bjarne-bachelorarbeit](https://huggingface.co/datasets/NPOA/Bjarne-Bachelorarbeit)
<!-- - **Language:** Unknown -->
<!-- - **License:** Unknown -->
### Model Sources
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
### Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False, 'architecture': 'XLMRobertaModel'})
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Usage
### Direct Usage (Sentence Transformers)
First install the Sentence Transformers library:
```bash
pip install -U sentence-transformers
```
Then you can load this model and run inference.
```python
from sentence_transformers import SentenceTransformer
# Download from the 🤗 Hub
model = SentenceTransformer("BjarneNPO/finetune_19_08_2025_12_45_15")
# Run inference
queries = [
"Login mit dem Authenticator funktioniert nicht mehr, Code ist immer ung\u00fcltig",
]
documents = [
'Nachdem die Uhrzeit neu synchronisiert war konnte sie sich wieder einloggen.',
'Erneut die Tätigkeit gelöscht und neu Übertragen, die Tätigkeit wurde aber nicht erneut angezeigt',
'Dies entspricht der Vorlage. muss Vorlage anpassen.',
]
query_embeddings = model.encode_query(queries)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# [1, 1024] [3, 1024]
# Get the similarity scores for the embeddings
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.6199, 0.3746, 0.3027]])
```
<!--
### Direct Usage (Transformers)
<details><summary>Click to see the direct usage in Transformers</summary>
</details>
-->
<!--
### Downstream Usage (Sentence Transformers)
You can finetune this model on your own dataset.
<details><summary>Click to expand</summary>
</details>
-->
<!--
### Out-of-Scope Use
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->
<!--
## Bias, Risks and Limitations
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->
<!--
### Recommendations
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->
## Training Details
### Training Dataset
#### bjarne-bachelorarbeit
* Dataset: [bjarne-bachelorarbeit](https://huggingface.co/datasets/NPOA/Bjarne-Bachelorarbeit) at [273f1a5](https://huggingface.co/datasets/NPOA/Bjarne-Bachelorarbeit/tree/273f1a515b2a1731a04a643cf39bd217d61a02a0)
* Size: 19,964 training samples
* Columns: <code>query</code> and <code>answer</code>
* Approximate statistics based on the first 1000 samples:
| | query | answer |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 27.66 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 22.87 tokens</li><li>max: 151 tokens</li></ul> |
* Samples:
| query | answer |
|:------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------|
| <code>Wie kann man die Jahresurlaubsübersicht exportieren?</code> | <code>über das 3 Punkte Menü rechts oben. Mitarbeiter auswählen und exportieren</code> |
| <code>1. Vertragsabschlüsse werden nicht übertragen
<br>2. Kinder kommen nicht von nach
<br>3. Absage kann bei Portalstatus nicht erstellt werden.</code> | <code>Ticket
<br>Userin gebeten sich an den Support zu wenden, da der Fehler liegt.</code> |
| <code>Wird im Anmeldeportal nicht gefunden.</code> | <code>Die Schnittstelle war noch nicht aktiviert und Profil ebenfalls nicht.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Evaluation Dataset
#### bjarne-bachelorarbeit
* Dataset: [bjarne-bachelorarbeit](https://huggingface.co/datasets/NPOA/Bjarne-Bachelorarbeit) at [273f1a5](https://huggingface.co/datasets/NPOA/Bjarne-Bachelorarbeit/tree/273f1a515b2a1731a04a643cf39bd217d61a02a0)
* Size: 8,557 evaluation samples
* Columns: <code>query</code> and <code>answer</code>
* Approximate statistics based on the first 1000 samples:
| | query | answer |
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|
| type | string | string |
| details | <ul><li>min: 4 tokens</li><li>mean: 26.49 tokens</li><li>max: 512 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 23.16 tokens</li><li>max: 512 tokens</li></ul> |
* Samples:
| query | answer |
|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| <code>Liebes Support Team!
<br>In unserer Kst. fiel der EL auf, dass es in der Urlaubsübersicht Unstimmigkeiten gibt. So werden z.B. bei der Kollegin 60 offene Tage angezeigt und im Detail (Jahresübersicht) korrekt alle eingetragenen Tage und nur 2 Tage Rest!
<br>Ich freue mich auf Ihre Rückmeldung.
<br>Mit besten Grüßen
<br>_________________________________________________
<br>Leitung Kompetenzteam
<br>Geschäftsfeld Kindertageseinrichtungen
<br> ()
<br> e.V.
<br>. 280
<br>33605
<br>Telefon: Mo.+Mi. +49 521 9216-129 Di., Do. + Fr. +49 5264 6559100
<br>E-Mail:
<br>Web: www.awo-owl.de
<br>Instagram: www.instagram.com/
<br>Facebook: www.facebook.com/
<br>Vorsitzende des Präsidiums und des Aufsichtsrates:
<br>Vorstand: (Vors.),
<br>Amtsgericht VR 1151
<br>Diese E-Mail einschließlich evtl. angehängter Dateien enthält vertrauliche und/oder rechtlich geschützte Informationen. Wenn Sie nicht der Adressat sind und diese E-Mail irrtümlich erhalten haben, dürfen Sie weder den Inhalt dieser E-Mail nutzen, noch dürfen Sie die eventuell angehängten Datei...</code> | <code>Problem ist bekannt und wird im Verlauf des Tages behoben.</code> |
| <code>hat im einen Vertrag, aber wurde nicht nach übertragen. war wegen fehlender Anbindung auf der Schnittstelle nicht auf der Anmeldeliste.</code> | <code>Kind muss manuell angelegt werden und dann neu synchronisiert und Anmeldedaten zusammenführen.
<br>Da Userin weiterhin Anmeldedaten nicht zusammenführen kann Userin gebeten uns einen Screenshot aus dem Kita-Navigator zukommen zu lassen.
<br>Beide Kinder wurden nun übertragen und befinden sich unter Vetragsangeboten.</code> |
| <code>Wie kann ein Kind aus den zukünftigen Neuaufnahmen gelöscht werden?</code> | <code>Benutzer muss erst die BI und kann dann über den Button Statuswechsel durchführen das ganze Kind löschen.</code> |
* Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#multiplenegativesrankingloss) with these parameters:
```json
{
"scale": 20.0,
"similarity_fct": "cos_sim",
"gather_across_devices": false
}
```
### Training Hyperparameters
#### Non-Default Hyperparameters
- `eval_strategy`: epoch
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `gradient_accumulation_steps`: 8
- `learning_rate`: 2e-05
- `lr_scheduler_type`: cosine
- `warmup_ratio`: 0.1
- `bf16`: True
- `tf32`: False
- `load_best_model_at_end`: True
- `batch_sampler`: no_duplicates
#### All Hyperparameters
<details><summary>Click to expand</summary>
- `overwrite_output_dir`: False
- `do_predict`: False
- `eval_strategy`: epoch
- `prediction_loss_only`: True
- `per_device_train_batch_size`: 16
- `per_device_eval_batch_size`: 16
- `per_gpu_train_batch_size`: None
- `per_gpu_eval_batch_size`: None
- `gradient_accumulation_steps`: 8
- `eval_accumulation_steps`: None
- `torch_empty_cache_steps`: None
- `learning_rate`: 2e-05
- `weight_decay`: 0.0
- `adam_beta1`: 0.9
- `adam_beta2`: 0.999
- `adam_epsilon`: 1e-08
- `max_grad_norm`: 1.0
- `num_train_epochs`: 3
- `max_steps`: -1
- `lr_scheduler_type`: cosine
- `lr_scheduler_kwargs`: {}
- `warmup_ratio`: 0.1
- `warmup_steps`: 0
- `log_level`: passive
- `log_level_replica`: warning
- `log_on_each_node`: True
- `logging_nan_inf_filter`: True
- `save_safetensors`: True
- `save_on_each_node`: False
- `save_only_model`: False
- `restore_callback_states_from_checkpoint`: False
- `no_cuda`: False
- `use_cpu`: False
- `use_mps_device`: False
- `seed`: 42
- `data_seed`: None
- `jit_mode_eval`: False
- `use_ipex`: False
- `bf16`: True
- `fp16`: False
- `fp16_opt_level`: O1
- `half_precision_backend`: auto
- `bf16_full_eval`: False
- `fp16_full_eval`: False
- `tf32`: False
- `local_rank`: 0
- `ddp_backend`: None
- `tpu_num_cores`: None
- `tpu_metrics_debug`: False
- `debug`: []
- `dataloader_drop_last`: False
- `dataloader_num_workers`: 0
- `dataloader_prefetch_factor`: None
- `past_index`: -1
- `disable_tqdm`: False
- `remove_unused_columns`: True
- `label_names`: None
- `load_best_model_at_end`: True
- `ignore_data_skip`: False
- `fsdp`: []
- `fsdp_min_num_params`: 0
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
- `fsdp_transformer_layer_cls_to_wrap`: None
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
- `deepspeed`: None
- `label_smoothing_factor`: 0.0
- `optim`: adamw_torch_fused
- `optim_args`: None
- `adafactor`: False
- `group_by_length`: False
- `length_column_name`: length
- `ddp_find_unused_parameters`: None
- `ddp_bucket_cap_mb`: None
- `ddp_broadcast_buffers`: False
- `dataloader_pin_memory`: True
- `dataloader_persistent_workers`: False
- `skip_memory_metrics`: True
- `use_legacy_prediction_loop`: False
- `push_to_hub`: False
- `resume_from_checkpoint`: None
- `hub_model_id`: None
- `hub_strategy`: every_save
- `hub_private_repo`: None
- `hub_always_push`: False
- `hub_revision`: None
- `gradient_checkpointing`: False
- `gradient_checkpointing_kwargs`: None
- `include_inputs_for_metrics`: False
- `include_for_metrics`: []
- `eval_do_concat_batches`: True
- `fp16_backend`: auto
- `push_to_hub_model_id`: None
- `push_to_hub_organization`: None
- `mp_parameters`:
- `auto_find_batch_size`: False
- `full_determinism`: False
- `torchdynamo`: None
- `ray_scope`: last
- `ddp_timeout`: 1800
- `torch_compile`: False
- `torch_compile_backend`: None
- `torch_compile_mode`: None
- `include_tokens_per_second`: False
- `include_num_input_tokens_seen`: False
- `neftune_noise_alpha`: None
- `optim_target_modules`: None
- `batch_eval_metrics`: False
- `eval_on_start`: False
- `use_liger_kernel`: False
- `liger_kernel_config`: None
- `eval_use_gather_object`: False
- `average_tokens_across_devices`: False
- `prompts`: None
- `batch_sampler`: no_duplicates
- `multi_dataset_batch_sampler`: proportional
- `router_mapping`: {}
- `learning_rate_mapping`: {}
</details>
### Training Logs
| Epoch | Step | Training Loss | Validation Loss |
|:-------:|:-------:|:-------------:|:---------------:|
| 0.0641 | 10 | 2.772 | - |
| 0.1282 | 20 | 2.7656 | - |
| 0.1923 | 30 | 2.7448 | - |
| 0.2564 | 40 | 2.674 | - |
| 0.3205 | 50 | 2.5086 | - |
| 0.3846 | 60 | 2.3308 | - |
| 0.4487 | 70 | 2.0376 | - |
| 0.5128 | 80 | 1.9653 | - |
| 0.5769 | 90 | 1.9202 | - |
| 0.6410 | 100 | 1.7578 | - |
| 0.7051 | 110 | 1.6882 | - |
| 0.7692 | 120 | 1.6155 | - |
| 0.8333 | 130 | 1.5431 | - |
| 0.8974 | 140 | 1.4487 | - |
| 0.9615 | 150 | 1.4125 | - |
| 1.0 | 156 | - | 1.3032 |
| 1.0256 | 160 | 1.3047 | - |
| 1.0897 | 170 | 1.2717 | - |
| 1.1538 | 180 | 1.2822 | - |
| 1.2179 | 190 | 1.243 | - |
| 1.2821 | 200 | 1.2183 | - |
| 1.3462 | 210 | 1.1533 | - |
| 1.4103 | 220 | 1.1534 | - |
| 1.4744 | 230 | 1.1748 | - |
| 1.5385 | 240 | 1.0993 | - |
| 1.6026 | 250 | 1.1418 | - |
| 1.6667 | 260 | 1.0975 | - |
| 1.7308 | 270 | 1.0359 | - |
| 1.7949 | 280 | 1.0728 | - |
| 1.8590 | 290 | 0.9835 | - |
| 1.9231 | 300 | 0.9846 | - |
| 1.9872 | 310 | 0.9811 | - |
| 2.0 | 312 | - | 0.9966 |
| 2.0513 | 320 | 0.8722 | - |
| 2.1154 | 330 | 0.8756 | - |
| 2.1795 | 340 | 0.9337 | - |
| 2.2436 | 350 | 0.9512 | - |
| 2.3077 | 360 | 0.915 | - |
| 2.3718 | 370 | 0.8729 | - |
| 2.4359 | 380 | 0.877 | - |
| 2.5 | 390 | 0.8838 | - |
| 2.5641 | 400 | 0.8603 | - |
| 2.6282 | 410 | 0.9071 | - |
| 2.6923 | 420 | 0.8661 | - |
| 2.7564 | 430 | 0.8705 | - |
| 2.8205 | 440 | 0.8752 | - |
| 2.8846 | 450 | 0.8926 | - |
| 2.9487 | 460 | 0.7818 | - |
| **3.0** | **468** | **-** | **0.9536** |
* The bold row denotes the saved checkpoint.
### Framework Versions
- Python: 3.12.11
- Sentence Transformers: 5.1.0
- Transformers: 4.55.2
- PyTorch: 2.8.0+cu128
- Accelerate: 1.10.0
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citation
### BibTeX
#### Sentence Transformers
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "https://arxiv.org/abs/1908.10084",
}
```
#### MultipleNegativesRankingLoss
```bibtex
@misc{henderson2017efficient,
title={Efficient Natural Language Response Suggestion for Smart Reply},
author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
year={2017},
eprint={1705.00652},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
<!--
## Glossary
*Clearly define terms in order to be accessible across audiences.*
-->
<!--
## Model Card Authors
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->
<!--
## Model Card Contact
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->
|
mmcarpi/corpus-carolina-100M-64K-tokenizer
|
mmcarpi
| 2025-08-19T12:52:25Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T01:33:07Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
jurgenpaul82/DECEIVER
|
jurgenpaul82
| 2025-08-19T12:50:57Z | 0 | 0 |
fasttext
|
[
"fasttext",
"music",
"climate",
"chemistry",
"biology",
"finance",
"text-generation-inference",
"merge",
"legal",
"am",
"dataset:MegaScience/MegaScience",
"dataset:fka/awesome-chatgpt-prompts",
"dataset:nvidia/Llama-Nemotron-VLM-Dataset-v1",
"dataset:jxm/gpt-oss20b-samples",
"dataset:nvidia/Granary",
"dataset:NousResearch/Hermes-3-Dataset",
"base_model:Qwen/Qwen3-Coder-480B-A35B-Instruct",
"base_model:finetune:Qwen/Qwen3-Coder-480B-A35B-Instruct",
"license:mit",
"region:us"
] | null | 2025-08-19T12:39:55Z |
---
license: mit
datasets:
- MegaScience/MegaScience
- fka/awesome-chatgpt-prompts
- nvidia/Llama-Nemotron-VLM-Dataset-v1
- jxm/gpt-oss20b-samples
- nvidia/Granary
- NousResearch/Hermes-3-Dataset
language:
- am
metrics:
- accuracy
- bertscore
- brier_score
- character
base_model:
- Qwen/Qwen3-Coder-480B-A35B-Instruct
new_version: tencent/Hunyuan-1.8B-Instruct
library_name: fasttext
tags:
- music
- climate
- chemistry
- biology
- finance
- text-generation-inference
- merge
- legal
---
|
Azurastar2903/Llama-3.2-3B-Instruct-rk3588-1.2.1
|
Azurastar2903
| 2025-08-19T12:48:06Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"facebook",
"meta",
"pytorch",
"llama-3",
"conversational",
"en",
"de",
"fr",
"it",
"pt",
"hi",
"es",
"th",
"arxiv:2204.05149",
"arxiv:2405.16406",
"license:llama3.2",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T12:45:38Z |
---
language:
- en
- de
- fr
- it
- pt
- hi
- es
- th
library_name: transformers
license: llama3.2
pipeline_tag: text-generation
tags:
- facebook
- meta
- pytorch
- llama
- llama-3
extra_gated_prompt: "### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT\n\nLlama 3.2 Version\
\ Release Date: September 25, 2024\n\n“Agreement” means the terms and conditions\
\ for use, reproduction, distribution and modification of the Llama Materials set\
\ forth herein.\n\n“Documentation” means the specifications, manuals and documentation\
\ accompanying Llama 3.2 distributed by Meta at https://llama.meta.com/doc/overview.\n\
\n“Licensee” or “you” means you, or your employer or any other person or entity\
\ (if you are entering into this Agreement on such person or entity’s behalf),\
\ of the age required under applicable laws, rules or regulations to provide legal\
\ consent and that has legal authority to bind your employer or such other person\
\ or entity if you are entering in this Agreement on their behalf.\n\n“Llama 3.2”\
\ means the foundational large language models and software and algorithms, including\
\ machine-learning model code, trained model weights, inference-enabling code, training-enabling\
\ code, fine-tuning enabling code and other elements of the foregoing distributed\
\ by Meta at https://www.llama.com/llama-downloads.\n\n“Llama Materials” means,\
\ collectively, Meta’s proprietary Llama 3.2 and Documentation (and any portion\
\ thereof) made available under this Agreement.\n\n“Meta” or “we” means Meta Platforms\
\ Ireland Limited (if you are located in or, if you are an entity, your principal\
\ place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if\
\ you are located outside of the EEA or Switzerland). \n\nBy clicking “I Accept”\
\ below or by using or distributing any portion or element of the Llama Materials,\
\ you agree to be bound by this Agreement.\n\n1. License Rights and Redistribution.\n\
a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable\
\ and royalty-free limited license under Meta’s intellectual property or other rights\
\ owned by Meta embodied in the Llama Materials to use, reproduce, distribute,\
\ copy, create derivative works of, and make modifications to the Llama Materials.\
\ \nb. Redistribution and Use. \ni. If you distribute or make available the Llama\
\ Materials (or any derivative works thereof), or a product or service (including\
\ another AI model) that contains any of them, you shall (A) provide a copy of this\
\ Agreement with any such Llama Materials; and (B) prominently display “Built with\
\ Llama” on a related website, user interface, blogpost, about page, or product\
\ documentation. If you use the Llama Materials or any outputs or results of the\
\ Llama Materials to create, train, fine tune, or otherwise improve an AI model,\
\ which is distributed or made available, you shall also include “Llama” at the\
\ beginning of any such AI model name.\nii. If you receive Llama Materials, or any\
\ derivative works thereof, from a Licensee as part of an integrated end user product,\
\ then Section 2 of this Agreement will not apply to you. \niii. You must retain\
\ in all copies of the Llama Materials that you distribute the following attribution\
\ notice within a “Notice” text file distributed as a part of such copies: “Llama\
\ 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,\
\ Inc. All Rights Reserved.”\niv. Your use of the Llama Materials must comply with\
\ applicable laws and regulations (including trade compliance laws and regulations)\
\ and adhere to the Acceptable Use Policy for the Llama Materials (available at\
\ https://www.llama.com/llama3_2/use-policy), which is hereby incorporated by reference\
\ into this Agreement.\n \n2. Additional Commercial Terms. If, on the Llama 3.2\
\ version release date, the monthly active users of the products or services made\
\ available by or for Licensee, or Licensee’s affiliates, is greater than 700 million\
\ monthly active users in the preceding calendar month, you must request a license\
\ from Meta, which Meta may grant to you in its sole discretion, and you are not\
\ authorized to exercise any of the rights under this Agreement unless or until\
\ Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS\
\ REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM\
\ ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS\
\ ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION,\
\ ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR\
\ PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING\
\ OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR\
\ USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability.\
\ IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY,\
\ WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING\
\ OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,\
\ INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE\
\ BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\n\
a. No trademark licenses are granted under this Agreement, and in connection with\
\ the Llama Materials, neither Meta nor Licensee may use any name or mark owned\
\ by or associated with the other or any of its affiliates, except as required\
\ for reasonable and customary use in describing and redistributing the Llama Materials\
\ or as set forth in this Section 5(a). Meta hereby grants you a license to use\
\ “Llama” (the “Mark”) solely as required to comply with the last sentence of Section\
\ 1.b.i. You will comply with Meta’s brand guidelines (currently accessible at\
\ https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising\
\ out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to\
\ Meta’s ownership of Llama Materials and derivatives made by or for Meta, with\
\ respect to any derivative works and modifications of the Llama Materials that\
\ are made by you, as between you and Meta, you are and will be the owner of such\
\ derivative works and modifications.\nc. If you institute litigation or other proceedings\
\ against Meta or any entity (including a cross-claim or counterclaim in a lawsuit)\
\ alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion\
\ of any of the foregoing, constitutes infringement of intellectual property or\
\ other rights owned or licensable by you, then any licenses granted to you under\
\ this Agreement shall terminate as of the date such litigation or claim is filed\
\ or instituted. You will indemnify and hold harmless Meta from and against any\
\ claim by any third party arising out of or related to your use or distribution\
\ of the Llama Materials.\n6. Term and Termination. The term of this Agreement will\
\ commence upon your acceptance of this Agreement or access to the Llama Materials\
\ and will continue in full force and effect until terminated in accordance with\
\ the terms and conditions herein. Meta may terminate this Agreement if you are\
\ in breach of any term or condition of this Agreement. Upon termination of this\
\ Agreement, you shall delete and cease use of the Llama Materials. Sections 3,\
\ 4 and 7 shall survive the termination of this Agreement. \n7. Governing Law and\
\ Jurisdiction. This Agreement will be governed and construed under the laws of\
\ the State of California without regard to choice of law principles, and the UN\
\ Convention on Contracts for the International Sale of Goods does not apply to\
\ this Agreement. The courts of California shall have exclusive jurisdiction of\
\ any dispute arising out of this Agreement. \n### Llama 3.2 Acceptable Use Policy\n\
Meta is committed to promoting safe and fair use of its tools and features, including\
\ Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy\
\ (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).\n\
#### Prohibited Uses\nWe want everyone to use Llama 3.2 safely and responsibly.\
\ You agree you will not use, or allow others to use, Llama 3.2 to:\n1. Violate\
\ the law or others’ rights, including to:\n 1. Engage in, promote, generate,\
\ contribute to, encourage, plan, incite, or further illegal or unlawful activity\
\ or content, such as:\n 1. Violence or terrorism\n 2. Exploitation\
\ or harm to children, including the solicitation, creation, acquisition, or dissemination\
\ of child exploitative content or failure to report Child Sexual Abuse Material\n\
\ 3. Human trafficking, exploitation, and sexual violence\n 4. The\
\ illegal distribution of information or materials to minors, including obscene\
\ materials, or failure to employ legally required age-gating in connection with\
\ such information or materials.\n 5. Sexual solicitation\n 6. Any\
\ other criminal activity\n 1. Engage in, promote, incite, or facilitate the\
\ harassment, abuse, threatening, or bullying of individuals or groups of individuals\n\
\ 2. Engage in, promote, incite, or facilitate discrimination or other unlawful\
\ or harmful conduct in the provision of employment, employment benefits, credit,\
\ housing, other economic benefits, or other essential goods and services\n 3.\
\ Engage in the unauthorized or unlicensed practice of any profession including,\
\ but not limited to, financial, legal, medical/health, or related professional\
\ practices\n 4. Collect, process, disclose, generate, or infer private or sensitive\
\ information about individuals, including information about individuals’ identity,\
\ health, or demographic information, unless you have obtained the right to do so\
\ in accordance with applicable law\n 5. Engage in or facilitate any action or\
\ generate any content that infringes, misappropriates, or otherwise violates any\
\ third-party rights, including the outputs or results of any products or services\
\ using the Llama Materials\n 6. Create, generate, or facilitate the creation\
\ of malicious code, malware, computer viruses or do anything else that could disable,\
\ overburden, interfere with or impair the proper working, integrity, operation\
\ or appearance of a website or computer system\n 7. Engage in any action, or\
\ facilitate any action, to intentionally circumvent or remove usage restrictions\
\ or other safety measures, or to enable functionality disabled by Meta \n2. Engage\
\ in, promote, incite, facilitate, or assist in the planning or development of activities\
\ that present a risk of death or bodily harm to individuals, including use of Llama\
\ 3.2 related to the following:\n 8. Military, warfare, nuclear industries or\
\ applications, espionage, use for materials or activities that are subject to the\
\ International Traffic Arms Regulations (ITAR) maintained by the United States\
\ Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989\
\ or the Chemical Weapons Convention Implementation Act of 1997\n 9. Guns and\
\ illegal weapons (including weapon development)\n 10. Illegal drugs and regulated/controlled\
\ substances\n 11. Operation of critical infrastructure, transportation technologies,\
\ or heavy machinery\n 12. Self-harm or harm to others, including suicide, cutting,\
\ and eating disorders\n 13. Any content intended to incite or promote violence,\
\ abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive\
\ or mislead others, including use of Llama 3.2 related to the following:\n 14.\
\ Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n\
\ 15. Generating, promoting, or furthering defamatory content, including the\
\ creation of defamatory statements, images, or other content\n 16. Generating,\
\ promoting, or further distributing spam\n 17. Impersonating another individual\
\ without consent, authorization, or legal right\n 18. Representing that the\
\ use of Llama 3.2 or outputs are human-generated\n 19. Generating or facilitating\
\ false online engagement, including fake reviews and other means of fake online\
\ engagement \n4. Fail to appropriately disclose to end users any known dangers\
\ of your AI system 5. Interact with third party tools, models, or software designed\
\ to generate unlawful content or engage in unlawful or harmful conduct and/or represent\
\ that the outputs of such tools, models, or software are associated with Meta or\
\ Llama 3.2\n\nWith respect to any multimodal models included in Llama 3.2, the\
\ rights granted under Section 1(a) of the Llama 3.2 Community License Agreement\
\ are not being granted to you if you are an individual domiciled in, or a company\
\ with a principal place of business in, the European Union. This restriction does\
\ not apply to end users of a product or service that incorporates any such multimodal\
\ models.\n\nPlease report any violation of this Policy, software “bug,” or other\
\ problems that could lead to a violation of this Policy through one of the following\
\ means:\n\n* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)\n\
* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)\n\
* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)\n\
* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama\
\ 3.2: LlamaUseReport@meta.com"
extra_gated_fields:
First Name: text
Last Name: text
Date of birth: date_picker
Country: country
Affiliation: text
Job title:
type: select
options:
- Student
- Research Graduate
- AI researcher
- AI developer/engineer
- Reporter
- Other
geo: ip_location
? By clicking Submit below I accept the terms of the license and acknowledge that
the information I provide will be collected stored processed and shared in accordance
with the Meta Privacy Policy
: checkbox
extra_gated_description: The information you provide will be collected, stored, processed
and shared in accordance with the [Meta Privacy Policy](https://www.facebook.com/privacy/policy/).
extra_gated_button_content: Submit
---
# Llama-3.2-3B-Instruct-RK3588-1.2.1
This version of Llama-3.2-3B-Instruct has been converted to run on the RK3588 NPU using ['w8a8', 'w8a8_g128', 'w8a8_g256'] quantization.
This model has been optimized with the following LoRA:
Compatible with RKLLM version: 1.2.1
## Useful links:
[Official RKLLM GitHub](https://github.com/airockchip/rknn-llm)
[RockhipNPU Reddit](https://reddit.com/r/RockchipNPU)
[EZRKNN-LLM](https://github.com/Pelochus/ezrknn-llm/)
Pretty much anything by these folks: [marty1885](https://github.com/marty1885) and [happyme531](https://huggingface.co/happyme531)
Converted using https://github.com/c0zaut/ez-er-rkllm-toolkit
# Original Model Card for base model, Llama-3.2-3B-Instruct, below:
## Model Information
The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks.
**Model Developer:** Meta
**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.
| | Training Data | Params | Input modalities | Output modalities | Context Length | GQA | Shared Embeddings | Token count | Knowledge cutoff |
| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
| Llama 3.2 (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 128k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
| Llama 3.2 Quantized (text only) | A new mix of publicly available online data. | 1B (1.23B) | Multilingual Text | Multilingual Text and code | 8k | Yes | Yes | Up to 9T tokens | December 2023 |
| | | 3B (3.21B) | Multilingual Text | Multilingual Text and code | | | | | |
**Supported Languages:** English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
**Model Release Date:** Sept 25, 2024
**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety.
**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
**Feedback:** Instructions on how to provide feedback or comments on the model can be found in the Llama Models [README](https://github.com/meta-llama/llama-models/blob/main/README.md). For more technical information about generation parameters and recipes for how to use Llama 3.2 in applications, please go [here](https://github.com/meta-llama/llama-recipes).
## Intended Use
**Intended Use Cases:** Llama 3.2 is intended for commercial and research use in multiple languages. Instruction tuned text only models are intended for assistant-like chat and agentic applications like knowledge retrieval and summarization, mobile AI powered writing assistants and query and prompt rewriting. Pretrained models can be adapted for a variety of additional natural language generation tasks. Similarly, quantized models can be adapted for a variety of on-device use-cases with limited compute resources.
**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
## How to use
This repository contains two versions of Llama-3.2-3B-Instruct, for use with `transformers` and with the original `llama` codebase.
### Use with transformers
Starting with `transformers >= 4.43.0` onward, you can run conversational inference using the Transformers `pipeline` abstraction or by leveraging the Auto classes with the `generate()` function.
Make sure to update your transformers installation via `pip install --upgrade transformers`.
```python
import torch
from transformers import pipeline
model_id = "meta-llama/Llama-3.2-3B-Instruct"
pipe = pipeline(
"text-generation",
model=model_id,
torch_dtype=torch.bfloat16,
device_map="auto",
)
messages = [
{"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
{"role": "user", "content": "Who are you?"},
]
outputs = pipe(
messages,
max_new_tokens=256,
)
print(outputs[0]["generated_text"][-1])
```
Note: You can also find detailed recipes on how to use the model locally, with `torch.compile()`, assisted generations, quantised and more at [`huggingface-llama-recipes`](https://github.com/huggingface/huggingface-llama-recipes)
### Use with `llama`
Please, follow the instructions in the [repository](https://github.com/meta-llama/llama)
To download Original checkpoints, see the example command below leveraging `huggingface-cli`:
```
huggingface-cli download meta-llama/Llama-3.2-3B-Instruct --include "original/*" --local-dir Llama-3.2-3B-Instruct
```
## Hardware and Software
**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, quantization, annotation, and evaluation were also performed on production infrastructure.
**Training Energy Use:** Training utilized a cumulative of **916k** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency.
**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **240** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy; therefore, the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
| | Training Time (GPU hours) | Logit Generation Time (GPU Hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
| :---- | :---: | ----- | :---: | :---: | :---: |
| Llama 3.2 1B | 370k | \- | 700 | 107 | 0 |
| Llama 3.2 3B | 460k | \- | 700 | 133 | 0 |
| Llama 3.2 1B SpinQuant | 1.7 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 3B SpinQuant | 2.4 | 0 | 700 | *Negligible*\*\* | 0 |
| Llama 3.2 1B QLora | 1.3k | 0 | 700 | 0.381 | 0 |
| Llama 3.2 3B QLora | 1.6k | 0 | 700 | 0.461 | 0 |
| Total | 833k | 86k | | 240 | 0 |
\*\* The location-based CO2e emissions of Llama 3.2 1B SpinQuant and Llama 3.2 3B SpinQuant are less than 0.001 metric tonnes each. This is due to the minimal training GPU hours that are required.
The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149). Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
## Training Data
**Overview:** Llama 3.2 was pretrained on up to 9 trillion tokens of data from publicly available sources. For the 1B and 3B Llama 3.2 models, we incorporated logits from the Llama 3.1 8B and 70B models into the pretraining stage of the model development, where outputs (logits) from these larger models were used as token-level targets. Knowledge distillation was used after pruning to recover performance. In post-training we used a similar recipe as Llama 3.1 and produced final chat models by doing several rounds of alignment on top of the pre-trained model. Each round involved Supervised Fine-Tuning (SFT), Rejection Sampling (RS), and Direct Preference Optimization (DPO).
**Data Freshness:** The pretraining data has a cutoff of December 2023\.
## Quantization
### Quantization Scheme
We designed the current quantization scheme with the [PyTorch’s ExecuTorch](https://github.com/pytorch/executorch) inference framework and Arm CPU backend in mind, taking into account metrics including model quality, prefill/decoding speed, and memory footprint. Our quantization scheme involves three parts:
- All linear layers in all transformer blocks are quantized to a 4-bit groupwise scheme (with a group size of 32) for weights and 8-bit per-token dynamic quantization for activations.
- The classification layer is quantized to 8-bit per-channel for weight and 8-bit per token dynamic quantization for activation.
- Similar to classification layer, an 8-bit per channel quantization is used for embedding layer.
### Quantization-Aware Training and LoRA
The quantization-aware training (QAT) with low-rank adaptation (LoRA) models went through only post-training stages, using the same data as the full precision models. To initialize QAT, we utilize BF16 Llama 3.2 model checkpoints obtained after supervised fine-tuning (SFT) and perform an additional full round of SFT training with QAT. We then freeze the backbone of the QAT model and perform another round of SFT with LoRA adaptors applied to all layers within the transformer block. Meanwhile, the LoRA adaptors' weights and activations are maintained in BF16. Because our approach is similar to QLoRA of Dettmers et al., (2023) (i.e., quantization followed by LoRA adapters), we refer this method as QLoRA. Finally, we fine-tune the resulting model (both backbone and LoRA adaptors) using direct preference optimization (DPO).
### SpinQuant
[SpinQuant](https://arxiv.org/abs/2405.16406) was applied, together with generative post-training quantization (GPTQ). For the SpinQuant rotation matrix fine-tuning, we optimized for 100 iterations, using 800 samples with sequence-length 2048 from the WikiText 2 dataset. For GPTQ, we used 128 samples from the same dataset with the same sequence-length.
## Benchmarks \- English Text
In this section, we report the results for Llama 3.2 models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
### Base Pretrained Models
| Category | Benchmark | \# Shots | Metric | Llama 3.2 1B | Llama 3.2 3B | Llama 3.1 8B |
| ----- | ----- | :---: | :---: | :---: | :---: | :---: |
| General | MMLU | 5 | macro\_avg/acc\_char | 32.2 | 58 | 66.7 |
| | AGIEval English | 3-5 | average/acc\_char | 23.3 | 39.2 | 47.8 |
| | ARC-Challenge | 25 | acc\_char | 32.8 | 69.1 | 79.7 |
| Reading comprehension | SQuAD | 1 | em | 49.2 | 67.7 | 77 |
| | QuAC (F1) | 1 | f1 | 37.9 | 42.9 | 44.9 |
| | DROP (F1) | 3 | f1 | 28.0 | 45.2 | 59.5 |
| Long Context | Needle in Haystack | 0 | em | 96.8 | 1 | 1 |
### Instruction Tuned Models
| Capability | | Benchmark | \# Shots | Metric | Llama 3.2 1B bf16 | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B bf16 | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | ----- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | | MMLU | 5 | macro\_avg/acc | 49.3 | 43.3 | 47.3 | 49.0 | 63.4 | 60.5 | 62 | 62.4 | 69.4 |
| Re-writing | | Open-rewrite eval | 0 | micro\_avg/rougeL | 41.6 | 39.2 | 40.9 | 41.2 | 40.1 | 40.3 | 40.8 | 40.7 | 40.9 |
| Summarization | | TLDR9+ (test) | 1 | rougeL | 16.8 | 14.9 | 16.7 | 16.8 | 19.0 | 19.1 | 19.2 | 19.1 | 17.2 |
| Instruction following | | IFEval | 0 | Avg(Prompt/Instruction acc Loose/Strict) | 59.5 | 51.5 | 58.4 | 55.6 | 77.4 | 73.9 | 73.5 | 75.9 | 80.4 |
| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |
| | | MATH (CoT) | 0 | final\_em | 30.6 | 20.5 | 25.3 | 31.0 | 48.0 | 44.2 | 45.3 | 49.2 | 51.9 |
| Reasoning | | ARC-C | 0 | acc | 59.4 | 54.3 | 57 | 60.7 | 78.6 | 75.6 | 77.6 | 77.6 | 83.4 |
| | | GPQA | 0 | acc | 27.2 | 25.9 | 26.3 | 25.9 | 32.8 | 32.8 | 31.7 | 33.9 | 32.8 |
| | | Hellaswag | 0 | acc | 41.2 | 38.1 | 41.3 | 41.5 | 69.8 | 66.3 | 68 | 66.3 | 78.7 |
| Tool Use | | BFCL V2 | 0 | acc | 25.7 | 14.3 | 15.9 | 23.7 | 67.0 | 53.4 | 60.1 | 63.5 | 67.1 |
| | | Nexus | 0 | macro\_avg/acc | 13.5 | 5.2 | 9.6 | 12.5 | 34.3 | 32.4 | 31.5 | 30.1 | 38.5 |
| Long Context | | InfiniteBench/En.QA | 0 | longbook\_qa/f1 | 20.3 | N/A | N/A | N/A | 19.8 | N/A | N/A | N/A | 27.3 |
| | | InfiniteBench/En.MC | 0 | longbook\_choice/acc | 38.0 | N/A | N/A | N/A | 63.3 | N/A | N/A | N/A | 72.2 |
| | | NIH/Multi-needle | 0 | recall | 75.0 | N/A | N/A | N/A | 84.7 | N/A | N/A | N/A | 98.8 |
| Multilingual | | MGSM (CoT) | 0 | em | 24.5 | 13.7 | 18.2 | 24.4 | 58.2 | 48.9 | 54.3 | 56.8 | 68.9 |
\*\*for comparison purposes only. Model not released.
### Multilingual Benchmarks
| Category | Benchmark | Language | Llama 3.2 1B | Llama 3.2 1B Vanilla PTQ\*\* | Llama 3.2 1B Spin Quant | Llama 3.2 1B QLoRA | Llama 3.2 3B | Llama 3.2 3B Vanilla PTQ\*\* | Llama 3.2 3B Spin Quant | Llama 3.2 3B QLoRA | Llama 3.1 8B |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| General | MMLU (5-shot, macro_avg/acc) | Portuguese | 39.8 | 34.9 | 38.9 | 40.2 | 54.5 | 50.9 | 53.3 | 53.4 | 62.1 |
| | | Spanish | 41.5 | 36.0 | 39.8 | 41.8 | 55.1 | 51.9 | 53.6 | 53.6 | 62.5 |
| | | Italian | 39.8 | 34.9 | 38.1 | 40.6 | 53.8 | 49.9 | 52.1 | 51.7 | 61.6 |
| | | German | 39.2 | 34.9 | 37.5 | 39.6 | 53.3 | 50.0 | 52.2 | 51.3 | 60.6 |
| | | French | 40.5 | 34.8 | 39.2 | 40.8 | 54.6 | 51.2 | 53.3 | 53.3 | 62.3 |
| | | Hindi | 33.5 | 30.0 | 32.1 | 34.0 | 43.3 | 40.4 | 42.0 | 42.1 | 50.9 |
| | | Thai | 34.7 | 31.2 | 32.4 | 34.9 | 44.5 | 41.3 | 44.0 | 42.2 | 50.3 |
\*\*for comparison purposes only. Model not released.
## Inference time
In the below table, we compare the performance metrics of different quantization methods (SpinQuant and QAT \+ LoRA) with the BF16 baseline. The evaluation was done using the [ExecuTorch](https://github.com/pytorch/executorch) framework as the inference engine, with the ARM CPU as a backend using Android OnePlus 12 device.
| Category | Decode (tokens/sec) | Time-to-first-token (sec) | Prefill (tokens/sec) | Model size (PTE file size in MB) | Memory size (RSS in MB) |
| :---- | ----- | ----- | ----- | ----- | ----- |
| 1B BF16 (baseline) | 19.2 | 1.0 | 60.3 | 2358 | 3,185 |
| 1B SpinQuant | 50.2 (2.6x) | 0.3 (-76.9%) | 260.5 (4.3x) | 1083 (-54.1%) | 1,921 (-39.7%) |
| 1B QLoRA | 45.8 (2.4x) | 0.3 (-76.0%) | 252.0 (4.2x) | 1127 (-52.2%) | 2,255 (-29.2%) |
| 3B BF16 (baseline) | 7.6 | 3.0 | 21.2 | 6129 | 7,419 |
| 3B SpinQuant | 19.7 (2.6x) | 0.7 (-76.4%) | 89.7 (4.2x) | 2435 (-60.3%) | 3,726 (-49.8%) |
| 3B QLoRA | 18.5 (2.4x) | 0.7 (-76.1%) | 88.8 (4.2x) | 2529 (-58.7%) | 4,060 (-45.3%) |
(\*) The performance measurement is done using an adb binary-based approach.
(\*\*) It is measured on an Android OnePlus 12 device.
(\*\*\*) Time-to-first-token (TTFT) is measured with prompt length=64
*Footnote:*
- *Decode (tokens/second) is for how quickly it keeps generating. Higher is better.*
- *Time-to-first-token (TTFT for shorthand) is for how fast it generates the first token for a given prompt. Lower is better.*
- *Prefill is the inverse of TTFT (aka 1/TTFT) in tokens/second. Higher is better*
- *Model size \- how big is the model, measured by, PTE file, a binary file format for ExecuTorch*
- *RSS size \- Memory usage in resident set size (RSS)*
## Responsibility & Safety
As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama
2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm
3. Provide protections for the community to help prevent the misuse of our models
### Responsible Deployment
**Approach:** Llama is a foundational technology designed to be used in a variety of use cases. Examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models, enabling the world to benefit from the technology power, by aligning our model safety for generic use cases and addressing a standard set of harms. Developers are then in the driver’s seat to tailor safety for their use cases, defining their own policies and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/).
#### Llama 3.2 Instruct
**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control.
**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
#### Llama 3.2 Systems
**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box.
### New Capabilities and Use Cases
**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well.
**Constrained Environments:** Llama 3.2 1B and 3B models are expected to be deployed in highly constrained environments, such as mobile devices. LLM Systems using smaller models will have a different alignment profile and safety/helpfulness tradeoff than more complex, larger systems. Developers should ensure the safety of their system meets the requirements of their use case. We recommend using lighter system safeguards for such use cases, like Llama Guard 3-1B or its mobile-optimized version.
### Evaluations
**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case.
**Red Teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
### Critical Risks
In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** Llama 3.2 1B and 3B models are smaller and less capable derivatives of Llama 3.1. For Llama 3.1 70B and 405B, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons and have determined that such testing also applies to the smaller 1B and 3B models.
**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.
**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s 1B and 3B models are smaller and less capable models than Llama 3.1 405B, we broadly believe that the testing conducted for the 405B model also applies to Llama 3.2 models.
### Community
**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists).
**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
## Ethical Considerations and Limitations
**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.
**Testing:** Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.
|
vwzyrraz7l/blockassist-bc-tall_hunting_vulture_1755606016
|
vwzyrraz7l
| 2025-08-19T12:46:39Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"tall hunting vulture",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T12:46:36Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- tall hunting vulture
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
uzunc/VLM
|
uzunc
| 2025-08-19T12:41:27Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"generated_from_trainer",
"trl",
"sft",
"base_model:HuggingFaceTB/SmolVLM-Instruct",
"base_model:finetune:HuggingFaceTB/SmolVLM-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T11:25:59Z |
---
base_model: HuggingFaceTB/SmolVLM-Instruct
library_name: transformers
model_name: VLM
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for VLM
This model is a fine-tuned version of [HuggingFaceTB/SmolVLM-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="uzunc/VLM", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.6.0+cu124
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
agurung/v3sft_qwen7B_25percent_lr_1e4_bptt_offset
|
agurung
| 2025-08-19T12:40:58Z | 42 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen2",
"text-generation",
"generated_from_trainer",
"trl",
"sft",
"conversational",
"base_model:Qwen/Qwen2.5-7B-Instruct",
"base_model:finetune:Qwen/Qwen2.5-7B-Instruct",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-14T03:44:43Z |
---
base_model: Qwen/Qwen2.5-7B-Instruct
library_name: transformers
model_name: v3sft_qwen7B_25percent_lr_1e4_bptt_offset
tags:
- generated_from_trainer
- trl
- sft
licence: license
---
# Model Card for v3sft_qwen7B_25percent_lr_1e4_bptt_offset
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="agurung/v3sft_qwen7B_25percent_lr_1e4_bptt_offset", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alexgurung/ncp_reasoning_projector/runs/gcnqs7xl)
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.53.3
- Pytorch: 2.7.0+cu128
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
chiniwini/davidmodel
|
chiniwini
| 2025-08-19T12:37:41Z | 0 | 0 |
diffusers
|
[
"diffusers",
"flux",
"lora",
"replicate",
"text-to-image",
"en",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"license:other",
"region:us"
] |
text-to-image
| 2025-08-19T12:04:01Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
tags:
- flux
- diffusers
- lora
- replicate
base_model: "black-forest-labs/FLUX.1-dev"
pipeline_tag: text-to-image
# widget:
# - text: >-
# prompt
# output:
# url: https://...
instance_prompt: TOK
---
# Davidmodel
<Gallery />
## About this LoRA
This is a [LoRA](https://replicate.com/docs/guides/working-with-loras) for the FLUX.1-dev text-to-image model. It can be used with diffusers or ComfyUI.
It was trained on [Replicate](https://replicate.com/) using AI toolkit: https://replicate.com/ostris/flux-dev-lora-trainer/train
## Trigger words
You should use `TOK` to trigger the image generation.
## Run this LoRA with an API using Replicate
```py
import replicate
input = {
"prompt": "TOK",
"lora_weights": "https://huggingface.co/chiniwini/davidmodel/resolve/main/lora.safetensors"
}
output = replicate.run(
"black-forest-labs/flux-dev-lora",
input=input
)
for index, item in enumerate(output):
with open(f"output_{index}.webp", "wb") as file:
file.write(item.read())
```
## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)
```py
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('chiniwini/davidmodel', weight_name='lora.safetensors')
image = pipeline('TOK').images[0]
```
For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)
## Training details
- Steps: 1000
- Learning rate: 0.0004
- LoRA rank: 16
## Contribute your own examples
You can use the [community tab](https://huggingface.co/chiniwini/davidmodel/discussions) to add images that show off what you’ve made with this LoRA.
|
tensorblock/Menlo_Lucy-128k-GGUF
|
tensorblock
| 2025-08-19T12:30:43Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"TensorBlock",
"GGUF",
"text-generation",
"en",
"base_model:Menlo/Lucy-128k",
"base_model:quantized:Menlo/Lucy-128k",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T12:10:23Z |
---
license: apache-2.0
language:
- en
base_model: Menlo/Lucy-128k
pipeline_tag: text-generation
library_name: transformers
tags:
- TensorBlock
- GGUF
---
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
[](https://tensorblock.co)
[](https://twitter.com/tensorblock_aoi)
[](https://discord.gg/Ej5NmeHFf2)
[](https://github.com/TensorBlock)
[](https://t.me/TensorBlock)
## Menlo/Lucy-128k - GGUF
<div style="text-align: left; margin: 20px 0;">
<a href="https://discord.com/invite/Ej5NmeHFf2" style="display: inline-block; padding: 10px 20px; background-color: #5865F2; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
Join our Discord to learn more about what we're building ↗
</a>
</div>
This repo contains GGUF format model files for [Menlo/Lucy-128k](https://huggingface.co/Menlo/Lucy-128k).
The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b5753](https://github.com/ggml-org/llama.cpp/commit/73e53dc834c0a2336cd104473af6897197b96277).
## Our projects
<table border="1" cellspacing="0" cellpadding="10">
<tr>
<th colspan="2" style="font-size: 25px;">Forge</th>
</tr>
<tr>
<th colspan="2">
<img src="https://imgur.com/faI5UKh.jpeg" alt="Forge Project" width="900"/>
</th>
</tr>
<tr>
<th colspan="2">An OpenAI-compatible multi-provider routing layer.</th>
</tr>
<tr>
<th colspan="2">
<a href="https://github.com/TensorBlock/forge" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">🚀 Try it now! 🚀</a>
</th>
</tr>
<tr>
<th style="font-size: 25px;">Awesome MCP Servers</th>
<th style="font-size: 25px;">TensorBlock Studio</th>
</tr>
<tr>
<th><img src="https://imgur.com/2Xov7B7.jpeg" alt="MCP Servers" width="450"/></th>
<th><img src="https://imgur.com/pJcmF5u.jpeg" alt="Studio" width="450"/></th>
</tr>
<tr>
<th>A comprehensive collection of Model Context Protocol (MCP) servers.</th>
<th>A lightweight, open, and extensible multi-LLM interaction studio.</th>
</tr>
<tr>
<th>
<a href="https://github.com/TensorBlock/awesome-mcp-servers" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">👀 See what we built 👀</a>
</th>
<th>
<a href="https://github.com/TensorBlock/TensorBlock-Studio" target="_blank" style="
display: inline-block;
padding: 8px 16px;
background-color: #FF7F50;
color: white;
text-decoration: none;
border-radius: 6px;
font-weight: bold;
font-family: sans-serif;
">👀 See what we built 👀</a>
</th>
</tr>
</table>
## Prompt template
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [Lucy-128k-Q2_K.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q2_K.gguf) | Q2_K | 0.778 GB | smallest, significant quality loss - not recommended for most purposes |
| [Lucy-128k-Q3_K_S.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q3_K_S.gguf) | Q3_K_S | 0.867 GB | very small, high quality loss |
| [Lucy-128k-Q3_K_M.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q3_K_M.gguf) | Q3_K_M | 0.940 GB | very small, high quality loss |
| [Lucy-128k-Q3_K_L.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q3_K_L.gguf) | Q3_K_L | 1.003 GB | small, substantial quality loss |
| [Lucy-128k-Q4_0.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q4_0.gguf) | Q4_0 | 1.054 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [Lucy-128k-Q4_K_S.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q4_K_S.gguf) | Q4_K_S | 1.060 GB | small, greater quality loss |
| [Lucy-128k-Q4_K_M.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q4_K_M.gguf) | Q4_K_M | 1.107 GB | medium, balanced quality - recommended |
| [Lucy-128k-Q5_0.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q5_0.gguf) | Q5_0 | 1.231 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [Lucy-128k-Q5_K_S.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q5_K_S.gguf) | Q5_K_S | 1.231 GB | large, low quality loss - recommended |
| [Lucy-128k-Q5_K_M.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q5_K_M.gguf) | Q5_K_M | 1.258 GB | large, very low quality loss - recommended |
| [Lucy-128k-Q6_K.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q6_K.gguf) | Q6_K | 1.418 GB | very large, extremely low quality loss |
| [Lucy-128k-Q8_0.gguf](https://huggingface.co/tensorblock/Menlo_Lucy-128k-GGUF/blob/main/Lucy-128k-Q8_0.gguf) | Q8_0 | 1.834 GB | very large, extremely low quality loss - not recommended |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/Menlo_Lucy-128k-GGUF --include "Lucy-128k-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
```shell
huggingface-cli download tensorblock/Menlo_Lucy-128k-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```
|
lilTAT/blockassist-bc-gentle_rugged_hare_1755606615
|
lilTAT
| 2025-08-19T12:30:42Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"gentle rugged hare",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T12:30:38Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- gentle rugged hare
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Sophie-Rain-Viral-video-original-XX/New.full.videos.Sophie.Rain.Spiderman.Viral.Video.Official.Tutorial
|
Sophie-Rain-Viral-video-original-XX
| 2025-08-19T12:26:57Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-19T12:26:47Z |
<a href="https://sdu.sk/AyL"><img src="https://files.qatarliving.com/event/2025/06/20/Jawan69_0-1749987397680.gif" alt="fsd" /></a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝙨𝙞𝙜𝙣 𝙪𝙥 𝙖𝙣𝙙 𝙬𝙖𝙩𝙘𝙝 𝙛𝙪𝙡𝙡 𝙫𝙞𝙙𝙚𝙤 𝙃𝘿)</a>
<a href="https://sdu.sk/AyL" rel="nofollow">🔴 ➤►𝐂𝐥𝐢𝐤 𝐇𝐞𝐫𝐞 𝐭𝐨👉👉 (𝐅𝐮𝐥𝐥 𝐯𝐢𝐝𝐞𝐨 𝐋𝐢𝐧𝐤)</a>
|
VoilaRaj/80_rHeBRC
|
VoilaRaj
| 2025-08-19T12:15:05Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-19T12:11:06Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
Tensavitprice/TensavitMexico
|
Tensavitprice
| 2025-08-19T12:14:56Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-08-19T12:14:04Z |
---
license: apache-2.0
---
¿Qué es Tensavit y cómo funciona?
Tensavit cápsula es una cápsula para la hipertensión especialmente formulada, diseñada para ayudar a controlar la presión arterial alta de forma natural. Actúa favoreciendo una circulación saludable, reduciendo la presión arterial y ayudando al corazón a funcionar de forma más eficiente. La cápsula promueve el equilibrio del sistema cardiovascular, ayudando al cuerpo a mantener niveles estables de presión arterial. Al mejorar el flujo sanguíneo y la eficiencia cardíaca general, reduce la fatiga y el estrés relacionados con la hipertensión. En resumen, Tensavit Pastillas ofrece una forma segura, natural y eficaz de apoyar la salud cardíaca y mantener una presión arterial normal Tensavit costo.
Sitio web oficial:<a href="https://www.nutritionsee.com/tensaviexico">www.Tensavit.com</a>
<p><a href="https://www.nutritionsee.com/tensaviexico"> <img src="https://www.nutritionsee.com/wp-content/uploads/2025/07/Tensavit-mexico.png" alt="enter image description here"> </a></p>
<a href="https://www.nutritionsee.com/tensaviexico">¡Compra ya! Haz clic en el enlace de abajo para más información y obtén un 50% de descuento. ¡Date prisa!</a>
Sitio web oficial:<a href="https://www.nutritionsee.com/tensaviexico">www.Tensavit.com</a>
|
LBST/t10_pick_and_place_smolvla_019000
|
LBST
| 2025-08-19T12:13:58Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"pick-and-place",
"smolvla",
"checkpoint-019000",
"region:us"
] |
robotics
| 2025-08-19T12:13:52Z |
---
library_name: lerobot
tags:
- robotics
- pick-and-place
- smolvla
- checkpoint-019000
---
# T08 Pick and Place Policy - Checkpoint 019000
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
## Model Details
- **Checkpoint**: 019000
- **Architecture**: SmolVLA
- **Task**: Pick and Place (T08)
- **Training Step**: 019000
## Usage
You can evaluate this model using LeRobot:
```bash
python -m lerobot.scripts.eval \
--policy.path=LBST/t10_pick_and_place_smolvla_019000 \
--env.type=<your_environment> \
--eval.n_episodes=10 \
--policy.device=cuda
```
## Files
- `config.json`: Policy configuration
- `model.safetensors`: Model weights in SafeTensors format
- `train_config.json`: Complete training configuration for reproducibility
## Parent Repository
This checkpoint was extracted from: [LBST/t10_pick_and_place_files](https://huggingface.co/LBST/t10_pick_and_place_files)
---
*Generated automatically from checkpoint 019000*
|
LBST/t10_pick_and_place_smolvla_015000
|
LBST
| 2025-08-19T12:12:19Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"pick-and-place",
"smolvla",
"checkpoint-015000",
"region:us"
] |
robotics
| 2025-08-19T12:12:13Z |
---
library_name: lerobot
tags:
- robotics
- pick-and-place
- smolvla
- checkpoint-015000
---
# T08 Pick and Place Policy - Checkpoint 015000
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
## Model Details
- **Checkpoint**: 015000
- **Architecture**: SmolVLA
- **Task**: Pick and Place (T08)
- **Training Step**: 015000
## Usage
You can evaluate this model using LeRobot:
```bash
python -m lerobot.scripts.eval \
--policy.path=LBST/t10_pick_and_place_smolvla_015000 \
--env.type=<your_environment> \
--eval.n_episodes=10 \
--policy.device=cuda
```
## Files
- `config.json`: Policy configuration
- `model.safetensors`: Model weights in SafeTensors format
- `train_config.json`: Complete training configuration for reproducibility
## Parent Repository
This checkpoint was extracted from: [LBST/t10_pick_and_place_files](https://huggingface.co/LBST/t10_pick_and_place_files)
---
*Generated automatically from checkpoint 015000*
|
pempekmangedd/blockassist-bc-patterned_sturdy_dolphin_1755603799
|
pempekmangedd
| 2025-08-19T12:11:00Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"patterned sturdy dolphin",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T12:10:57Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- patterned sturdy dolphin
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
SirAB/Dolphin-gemma2-2b-finetuned-v2
|
SirAB
| 2025-08-19T12:11:00Z | 29 | 1 |
transformers
|
[
"transformers",
"safetensors",
"gemma2",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"base_model:SirAB/Dolphin-gemma2-2b-finetuned-v2",
"base_model:finetune:SirAB/Dolphin-gemma2-2b-finetuned-v2",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-06-10T09:34:21Z |
---
base_model: SirAB/Dolphin-gemma2-2b-finetuned-v2
tags:
- text-generation-inference
- transformers
- unsloth
- gemma2
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** SirAB
- **License:** apache-2.0
- **Finetuned from model :** SirAB/Dolphin-gemma2-2b-finetuned-v2
This gemma2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755603621
|
katanyasekolah
| 2025-08-19T12:10:15Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"silky sprightly cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T12:10:11Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- silky sprightly cassowary
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
LBST/t10_pick_and_place_smolvla_009000
|
LBST
| 2025-08-19T12:09:43Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"pick-and-place",
"smolvla",
"checkpoint-009000",
"region:us"
] |
robotics
| 2025-08-19T12:09:36Z |
---
library_name: lerobot
tags:
- robotics
- pick-and-place
- smolvla
- checkpoint-009000
---
# T08 Pick and Place Policy - Checkpoint 009000
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
## Model Details
- **Checkpoint**: 009000
- **Architecture**: SmolVLA
- **Task**: Pick and Place (T08)
- **Training Step**: 009000
## Usage
You can evaluate this model using LeRobot:
```bash
python -m lerobot.scripts.eval \
--policy.path=LBST/t10_pick_and_place_smolvla_009000 \
--env.type=<your_environment> \
--eval.n_episodes=10 \
--policy.device=cuda
```
## Files
- `config.json`: Policy configuration
- `model.safetensors`: Model weights in SafeTensors format
- `train_config.json`: Complete training configuration for reproducibility
## Parent Repository
This checkpoint was extracted from: [LBST/t10_pick_and_place_files](https://huggingface.co/LBST/t10_pick_and_place_files)
---
*Generated automatically from checkpoint 009000*
|
LBST/t10_pick_and_place_smolvla_007000
|
LBST
| 2025-08-19T12:08:55Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"pick-and-place",
"smolvla",
"checkpoint-007000",
"region:us"
] |
robotics
| 2025-08-19T12:08:48Z |
---
library_name: lerobot
tags:
- robotics
- pick-and-place
- smolvla
- checkpoint-007000
---
# T08 Pick and Place Policy - Checkpoint 007000
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
## Model Details
- **Checkpoint**: 007000
- **Architecture**: SmolVLA
- **Task**: Pick and Place (T08)
- **Training Step**: 007000
## Usage
You can evaluate this model using LeRobot:
```bash
python -m lerobot.scripts.eval \
--policy.path=LBST/t10_pick_and_place_smolvla_007000 \
--env.type=<your_environment> \
--eval.n_episodes=10 \
--policy.device=cuda
```
## Files
- `config.json`: Policy configuration
- `model.safetensors`: Model weights in SafeTensors format
- `train_config.json`: Complete training configuration for reproducibility
## Parent Repository
This checkpoint was extracted from: [LBST/t10_pick_and_place_files](https://huggingface.co/LBST/t10_pick_and_place_files)
---
*Generated automatically from checkpoint 007000*
|
LBST/t10_pick_and_place_smolvla_006000
|
LBST
| 2025-08-19T12:08:28Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"pick-and-place",
"smolvla",
"checkpoint-006000",
"region:us"
] |
robotics
| 2025-08-19T12:08:23Z |
---
library_name: lerobot
tags:
- robotics
- pick-and-place
- smolvla
- checkpoint-006000
---
# T08 Pick and Place Policy - Checkpoint 006000
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
## Model Details
- **Checkpoint**: 006000
- **Architecture**: SmolVLA
- **Task**: Pick and Place (T08)
- **Training Step**: 006000
## Usage
You can evaluate this model using LeRobot:
```bash
python -m lerobot.scripts.eval \
--policy.path=LBST/t10_pick_and_place_smolvla_006000 \
--env.type=<your_environment> \
--eval.n_episodes=10 \
--policy.device=cuda
```
## Files
- `config.json`: Policy configuration
- `model.safetensors`: Model weights in SafeTensors format
- `train_config.json`: Complete training configuration for reproducibility
## Parent Repository
This checkpoint was extracted from: [LBST/t10_pick_and_place_files](https://huggingface.co/LBST/t10_pick_and_place_files)
---
*Generated automatically from checkpoint 006000*
|
LBST/t10_pick_and_place_smolvla_001000
|
LBST
| 2025-08-19T12:05:56Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"pick-and-place",
"smolvla",
"checkpoint-001000",
"region:us"
] |
robotics
| 2025-08-19T12:05:44Z |
---
library_name: lerobot
tags:
- robotics
- pick-and-place
- smolvla
- checkpoint-001000
---
# T08 Pick and Place Policy - Checkpoint 001000
This model is a checkpoint from the training of a pick-and-place policy using SmolVLA architecture.
## Model Details
- **Checkpoint**: 001000
- **Architecture**: SmolVLA
- **Task**: Pick and Place (T08)
- **Training Step**: 001000
## Usage
You can evaluate this model using LeRobot:
```bash
python -m lerobot.scripts.eval \
--policy.path=LBST/t10_pick_and_place_smolvla_001000 \
--env.type=<your_environment> \
--eval.n_episodes=10 \
--policy.device=cuda
```
## Files
- `config.json`: Policy configuration
- `model.safetensors`: Model weights in SafeTensors format
- `train_config.json`: Complete training configuration for reproducibility
## Parent Repository
This checkpoint was extracted from: [LBST/t10_pick_and_place_files](https://huggingface.co/LBST/t10_pick_and_place_files)
---
*Generated automatically from checkpoint 001000*
|
musdbi/bpce_model
|
musdbi
| 2025-08-19T12:00:37Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"llama",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T12:00:27Z |
---
base_model: unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** musdbi
- **License:** apache-2.0
- **Finetuned from model :** unsloth/meta-llama-3.1-8b-instruct-bnb-4bit
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
swiptit/blockassist-bc-polished_armored_mandrill_1755604721
|
swiptit
| 2025-08-19T11:59:23Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"polished armored mandrill",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T11:59:19Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- polished armored mandrill
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
vg-sentry/Qwen-Qwen2.5-Coder-7B-Instruct-sentry-v1
|
vg-sentry
| 2025-08-19T11:59:11Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"generated_from_trainer",
"sft",
"trl",
"unsloth",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T11:07:28Z |
---
base_model: unsloth/qwen2.5-coder-7b-instruct-bnb-4bit
library_name: transformers
model_name: Qwen-Qwen2.5-Coder-7B-Instruct-sentry-v1
tags:
- generated_from_trainer
- sft
- trl
- unsloth
licence: license
---
# Model Card for Qwen-Qwen2.5-Coder-7B-Instruct-sentry-v1
This model is a fine-tuned version of [unsloth/qwen2.5-coder-7b-instruct-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-coder-7b-instruct-bnb-4bit).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="vg-sentry/Qwen-Qwen2.5-Coder-7B-Instruct-sentry-v1", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.6.0+cu124
- Datasets: 4.0.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
VoilaRaj/80_myjmKE
|
VoilaRaj
| 2025-08-19T11:58:26Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-19T11:54:40Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
indoempatnol/blockassist-bc-fishy_wary_swan_1755602935
|
indoempatnol
| 2025-08-19T11:56:18Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"fishy wary swan",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T11:56:14Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- fishy wary swan
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
TuKoResearch/WavCochV8192
|
TuKoResearch
| 2025-08-19T11:34:53Z | 318 | 0 |
transformers
|
[
"transformers",
"safetensors",
"WavCoch.WavCoch",
"feature-extraction",
"audio",
"speech",
"tokenizer",
"quantizer",
"cochlear",
"custom_code",
"en",
"license:apache-2.0",
"region:us"
] |
feature-extraction
| 2025-04-15T23:01:03Z |
---
language:
- en
library_name: transformers
pipeline_tag: feature-extraction
tags:
- audio
- speech
- tokenizer
- quantizer
- cochlear
- custom_code
license: apache-2.0 # ← adjust if different
pretty_name: WavCoch (8192-code speech tokenizer)
---
# WavCochV8192 — 8,192-code speech tokenizer (cochlear tokens)
**WavCochV8192** is a biologically-inspired, learned **audio quantizer** that maps a raw waveform to **discrete "cochlear tokens".** It is used as the tokenizer for the AuriStream autoregressive speech/language model (e.g., [TuKoResearch/AuriStream1B_librilight_ckpt500k](https://huggingface.co/TuKoResearch/AuriStream1B_librilight_ckpt500k)). The model is trained on LibriSpeech960 and encodes audio into a time–frequency representation ([Cochleagram; Feather et al., 2023 Nat Neuro](https://github.com/jenellefeather/chcochleagram)) and reads out **8,192-way discrete codes** through a low-bit latent bottleneck (LFQ). These tokens can be fed to a transformer LM for **representation learning** and **next-token prediction** (speech continuation).
> **API at a glance**
> - **Input:** mono waveform at 16 kHz (pytorch tensor float32), shape **(B, 1, T)**
> - **Output:** token IDs, shape **(B, L)** returned as dictionary under key **`"input_ids"`**
> - Implemented as a `transformers` custom model — load with `trust_remote_code=True`.
---
## Installation
```bash
pip install -U torch torchaudio transformers
```
---
## Quickstart — Quantize a waveform into cochlear tokens
```python
import torch, torchaudio
from transformers import AutoModel
device = "cuda" if torch.cuda.is_available() else "cpu"
# Load the quantizer
quantizer = AutoModel.from_pretrained(
"TuKoResearch/WavCochV8192", trust_remote_code=True
).to(device).eval()
# Load & prep audio (mono, 16 kHz)
wav, sr = torchaudio.load("sample.wav")
if wav.size(0) > 1: # stereo -> mono
wav = wav.mean(dim=0, keepdim=True)
if sr != 16_000:
wav = torchaudio.transforms.Resample(sr, 16_000)(wav)
sr = 16_000
# Forward pass — returns a dict with "input_ids" = (B, L)
with torch.no_grad():
out = quantizer(wav.unsqueeze(0).to(device)) # (1, 1, T) -> dict
token_ids = out["input_ids"] # LongTensor (1, L)
print("Token IDs shape:", token_ids.shape)
```
---
## Intended uses & limitations
- **Uses:** tokenization for speech LM training; compact storage/streaming of speech as discrete IDs, loosely inspired by human biology.
- **Limitations:** trained only on spoken English, so might not perform as well for other languages and non-speech sounds.
---
## Citation
If you use this tokenizer please cite:
```bibtex
@inproceedings{tuckute2025cochleartokens,
title = {Representing Speech Through Autoregressive Prediction of Cochlear Tokens},
author = {Greta Tuckute and Klemen Kotar and Evelina Fedorenko and Daniel Yamins},
booktitle = {Interspeech 2025},
year = {2025},
pages = {2180--2184},
doi = {10.21437/Interspeech.2025-2044},
issn = {2958-1796}
}
```
---
## Related
- **AuriStream LM:** https://huggingface.co/TuKoResearch/AuriStream1B_librilight_ckpt500k
- **Org:** https://huggingface.co/TuKoResearch
|
katanyasekolah/blockassist-bc-silky_sprightly_cassowary_1755601470
|
katanyasekolah
| 2025-08-19T11:33:45Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"silky sprightly cassowary",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T11:33:41Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- silky sprightly cassowary
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
imanuelradityaa/finetuned_cs_gemma_900_steps_16bit
|
imanuelradityaa
| 2025-08-19T11:32:58Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"gemma",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"base_model:unsloth/gemma-2b-it-bnb-4bit",
"base_model:finetune:unsloth/gemma-2b-it-bnb-4bit",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"8-bit",
"region:us"
] |
text-generation
| 2025-08-19T11:30:51Z |
---
base_model: unsloth/gemma-2b-it-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- gemma
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** imanuelradityaa
- **License:** apache-2.0
- **Finetuned from model :** unsloth/gemma-2b-it-bnb-4bit
This gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
phospho-app/Deimos252-ACT_BBOX-deimos_dataset-0ztq8
|
phospho-app
| 2025-08-19T11:28:36Z | 0 | 0 |
phosphobot
|
[
"phosphobot",
"safetensors",
"act",
"robotics",
"dataset:phospho-app/deimos_dataset_bboxes",
"region:us"
] |
robotics
| 2025-08-19T10:58:48Z |
---
datasets: phospho-app/deimos_dataset_bboxes
library_name: phosphobot
pipeline_tag: robotics
model_name: act
tags:
- phosphobot
- act
task_categories:
- robotics
---
# act Model - phospho Training Pipeline
## This model was trained using **phospho**.
Training was successful, try it out on your robot!
## Training parameters:
- **Dataset**: [phospho-app/deimos_dataset_bboxes](https://huggingface.co/datasets/phospho-app/deimos_dataset_bboxes)
- **Wandb run URL**: None
- **Epochs**: None
- **Batch size**: 100
- **Training steps**: 10000
📖 **Get Started**: [docs.phospho.ai](https://docs.phospho.ai?utm_source=huggingface_readme)
🤖 **Get your robot**: [robots.phospho.ai](https://robots.phospho.ai?utm_source=huggingface_readme)
|
hzk886/LLM
|
hzk886
| 2025-08-19T11:15:49Z | 0 | 0 | null |
[
"safetensors",
"camembert",
"arxiv:1910.09700",
"region:us"
] | null | 2025-08-19T11:04:26Z |
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
koloni/blockassist-bc-deadly_graceful_stingray_1755600447
|
koloni
| 2025-08-19T11:15:34Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T11:15:30Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- deadly graceful stingray
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
strangerzonehf/Flux-Ultimate-LoRA-Collection
|
strangerzonehf
| 2025-08-19T11:13:12Z | 5,964 | 104 |
diffusers
|
[
"diffusers",
"Flux.1-Dev",
"lora",
"Collections",
"SOTA",
"Realism",
"Diffusion",
"art",
"FLUX",
"image-to-image",
"text-to-image",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"doi:10.57967/hf/5698",
"license:other",
"region:us"
] |
text-to-image
| 2024-11-18T06:47:02Z |
---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
widget:
- text: Stranger Zones Ultimate LoRA Collection
output:
url: images/11.png
base_model:
- black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
library_name: diffusers
tags:
- Flux.1-Dev
- lora
- Collections
- SOTA
- Realism
- Diffusion
- art
- FLUX
- image-to-image
---
## Flux.1dev Adapter Resources
| File Name | Size | LFS | File Type |
|------------------------------------------------|--------|------|-----------------|
| 3DXL-Mannequin.safetensors | 613 MB | LFS | .safetensors |
| 3DXLC1.safetensors | 613 MB | LFS | .safetensors |
| 3DXLP1.safetensors | 613 MB | LFS | .safetensors |
| 3DXLP2.safetensors | 613 MB | LFS | .safetensors |
| 3DXLP3.safetensors | 613 MB | LFS | .safetensors |
| 3DXLP4.safetensors | 613 MB | LFS | .safetensors |
| 3DXLP5.safetensors | 613 MB | LFS | .safetensors |
| 3DXLP6.safetensors | 613 MB | LFS | .safetensors |
| Abstract-Cartoon.safetensors | 613 MB | LFS | .safetensors |
| Amxtoon.safetensors | 613 MB | LFS | .safetensors |
| Animeo.safetensors | 613 MB | LFS | .safetensors |
| Animex.safetensors | 613 MB | LFS | .safetensors |
| Aura-9999.safetensors | 613 MB | LFS | .safetensors |
| Bold-Shadows.safetensors | 613 MB | LFS | .safetensors |
| C33.safetensors | 613 MB | LFS | .safetensors |
| CAM00.safetensors | 613 MB | LFS | .safetensors |
| Canopus-Anime-Character-Art-FluxDev-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Canopus-Car-Flux-Dev-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Canopus-Clothing-Flux-Dev-Florence2-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Canopus-Cute-Kawaii-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Castor-3D-Portrait-Flux-LoRA.safetensors | 306 MB | LFS | .safetensors |
| Castor-3D-Sketchfab-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Castor-Character-Polygon-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Castor-Collage-Dim-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Castor-Happy-Halloween-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Castor-Red-Dead-Redemption-2-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Claymation.safetensors | 613 MB | LFS | .safetensors |
| Clothing-Flux-Dev-Florence2-LoRA-Pruned.safetensors | 613 MB | LFS | .safetensors |
| Clouds Illusion.safetensors | 613 MB | LFS | .safetensors |
| Creative-Stocks.safetensors | 613 MB | LFS | .safetensors |
| Cute-3d-Kawaii.safetensors | 613 MB | LFS | .safetensors |
| Dark_Creature.safetensors | 613 MB | LFS | .safetensors |
| Digital-Chaos.safetensors | 613 MB | LFS | .safetensors |
| Digital-Yellow.safetensors | 613 MB | LFS | .safetensors |
| Dramatic-Neon-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| EBook-Cover.safetensors | 613 MB | LFS | .safetensors |
| Electric-Blue.safetensors | 613 MB | LFS | .safetensors |
| Fashion-Modeling.safetensors | 613 MB | LFS | .safetensors |
| Flux-Dev-Real-Anime-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Flux-Realism-FineDetailed.safetensors | 613 MB | LFS | .safetensors |
| GArt.safetensors | 613 MB | LFS | .safetensors |
| Ghibli-Art.safetensors | 613 MB | LFS | .safetensors |
| Glowing-Body.safetensors | 613 MB | LFS | .safetensors |
| Golden-Coin.safetensors | 613 MB | LFS | .safetensors |
| Green-Cartoon.safetensors | 613 MB | LFS | .safetensors |
| Gta6-Concept-Charecter.safetensors | 613 MB | LFS | .safetensors |
| Gta6.safetensors | 613 MB | LFS | .safetensors |
| HDR-Digital-Chaos.safetensors | 613 MB | LFS | .safetensors |
| HDR.safetensors | 613 MB | LFS | .safetensors |
| Icon-Kit.safetensors | 613 MB | LFS | .safetensors |
| Intense-Red.safetensors | 613 MB | LFS | .safetensors |
| Isometric-3D-Cinematography.safetensors | 613 MB | LFS | .safetensors |
| Isometric-3D.safetensors | 613 MB | LFS | .safetensors |
| Kepler-452b-LoRA-Flux-Dev-3D-Bubbly.safetensors | 613 MB | LFS | .safetensors |
| Knitted- Character.safetensors | 613 MB | LFS | .safetensors |
| Lego.safetensors | 613 MB | LFS | .safetensors |
| Lime-Green.safetensors | 613 MB | LFS | .safetensors |
| Logo-design.safetensors | 613 MB | LFS | .safetensors |
| Long-Toon.safetensors | 613 MB | LFS | .safetensors |
| Minimal-Futuristic.safetensors | 613 MB | LFS | .safetensors |
| Mockup-Texture.safetensors | 613 MB | LFS | .safetensors |
| Multi-Frame-Shot(MFS).safetensors | 613 MB | LFS | .safetensors |
| NFTv4.safetensors | 613 MB | LFS | .safetensors |
| Orange-Chroma.safetensors | 613 MB | LFS | .safetensors |
| Past-Present-Deep-Mix-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Pastel-BG.safetensors | 613 MB | LFS | .safetensors |
| Prod-Ad.safetensors | 613 MB | LFS | .safetensors |
| Purple-Dreamy.safetensors | 613 MB | LFS | .safetensors |
| Purple_Grid.safetensors | 613 MB | LFS | .safetensors |
| Red-Undersea.safetensors | 613 MB | LFS | .safetensors |
| Retro-Pixel.safetensors | 613 MB | LFS | .safetensors |
| Seamless-Pattern-Design.safetensors | 613 MB | LFS | .safetensors |
| Shadow-Projection.safetensors | 613 MB | LFS | .safetensors |
| Simple_ Doodle.safetensors | 270 MB | LFS | .safetensors |
| Smiley-C4C.safetensors | 613 MB | LFS | .safetensors |
| Snoopy-Charlie-Brown-Flux-LoRA.safetensors | 613 MB | LFS | .safetensors |
| Street_Bokeh.safetensors | 613 MB | LFS | .safetensors |
| Super-Blend.safetensors | 613 MB | LFS | .safetensors |
| Super-Detail.safetensors | 613 MB | LFS | .safetensors |
| Super-Portrait.safetensors | 613 MB | LFS | .safetensors |
| Tarot-card.safetensors | 613 MB | LFS | .safetensors |
| Teen-Outfit.safetensors | 613 MB | LFS | .safetensors |
| Typography.safetensors | 613 MB | LFS | .safetensors |
| Uncoloured-3D-Polygon.safetensors | 613 MB | LFS | .safetensors |
| Yellow-Laser.safetensors | 613 MB | LFS | .safetensors |
| Yellow_Pop.safetensors | 613 MB | LFS | .safetensors |
| capybara-hf.safetensors | 613 MB | LFS | .safetensors |
| chill-guy.safetensors | 613 MB | LFS | .safetensors |
| coloring-book.safetensors | 613 MB | LFS | .safetensors |
| ctoon.safetensors | 613 MB | LFS | .safetensors |
| dalle-mix.safetensors | 613 MB | LFS | .safetensors |
| frosted-gc.safetensors | 613 MB | LFS | .safetensors |
| handstick69.safetensors | 613 MB | LFS | .safetensors |
| indo-realism.safetensors | 613 MB | LFS | .safetensors |
| look-in-2.safetensors | 613 MB | LFS | .safetensors |
| meme.safetensors | 613 MB | LFS | .safetensors |
| midjourney-mix.safetensors | 613 MB | LFS | .safetensors |
| mjV6.safetensors | 613 MB | LFS | .safetensors |
| movieboard.safetensors | 613 MB | LFS | .safetensors |
| nm99.safetensors | 613 MB | LFS | .safetensors |
| only-stickers.safetensors | 613 MB | LFS | .safetensors |
| polaroid-plus.safetensors | 613 MB | LFS | .safetensors |
| poster-foss.safetensors | 613 MB | LFS | .safetensors |
| quoter.safetensors | 613 MB | LFS | .safetensors |
| sketchcard.safetensors | 613 MB | LFS | .safetensors |
| stam9.safetensors | 613 MB | LFS | .safetensors |
| super-realism.safetensors | 613 MB | LFS | .safetensors |
| toon-mix.safetensors | 613 MB | LFS | .safetensors |
| toonic2.5D.safetensors | 613 MB | LFS | .safetensors |
| ywl-realism.safetensors | 613 MB | LFS | .safetensors |
<Gallery />
| **Repository** | **Description** | **Link** |
|-----------------------------|-------------------------------------------------------------|---------------------------------------------------|
| PrithivMLMods | Repository featuring various adapters and ML models. | [Visit Repository](https://huggingface.co/prithivMLmods) |
| StrangerZoneHF | Repository containing specialized Hugging Face models. | [Visit Repository](https://huggingface.co/strangerzonehf) |
------------------------------------------------------------------------------------------------------------------------------------------
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755600119
|
lisaozill03
| 2025-08-19T11:06:51Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T11:06:48Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VoilaRaj/80_NNpkgY
|
VoilaRaj
| 2025-08-19T11:04:54Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-19T11:00:54Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
JackTheKing/Qwen2.5-0.5B-FT
|
JackTheKing
| 2025-08-19T11:04:02Z | 0 | 0 | null |
[
"gguf",
"qwen2",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T10:56:40Z |
---
license: apache-2.0
---
|
kittygirlhere/blockassist-bc-twitchy_beaked_coral_1755601270
|
kittygirlhere
| 2025-08-19T11:01:54Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"twitchy beaked coral",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T11:01:50Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- twitchy beaked coral
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
lqpl/blockassist-bc-hairy_insectivorous_antelope_1755600734
|
lqpl
| 2025-08-19T10:55:20Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"hairy insectivorous antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:54:26Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- hairy insectivorous antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755600753
|
0xaoyama
| 2025-08-19T10:53:08Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:52:57Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
hzk886/dummy-model
|
hzk886
| 2025-08-19T10:52:12Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"camembert",
"fill-mask",
"arxiv:1910.09700",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
fill-mask
| 2025-08-19T10:51:28Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
ShimotsukiArc/Qwen2.5-Coder-7B-Instruct-trained3
|
ShimotsukiArc
| 2025-08-19T10:50:31Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2",
"trl",
"en",
"base_model:ShimotsukiArc/Qwen2.5-Coder-7B-Instruct-untrained",
"base_model:finetune:ShimotsukiArc/Qwen2.5-Coder-7B-Instruct-untrained",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T10:49:26Z |
---
base_model: ShimotsukiArc/Qwen2.5-Coder-7B-Instruct-untrained
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** ShimotsukiArc
- **License:** apache-2.0
- **Finetuned from model :** ShimotsukiArc/Qwen2.5-Coder-7B-Instruct-untrained
This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
KCS97/wolf_plushie
|
KCS97
| 2025-08-19T10:48:58Z | 0 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"text-to-image",
"dreambooth",
"diffusers-training",
"stable-diffusion",
"stable-diffusion-diffusers",
"base_model:stable-diffusion-v1-5/stable-diffusion-v1-5",
"base_model:finetune:stable-diffusion-v1-5/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2025-08-19T10:36:29Z |
---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
instance_prompt: a photo of sks plushie
tags:
- text-to-image
- dreambooth
- diffusers-training
- stable-diffusion
- stable-diffusion-diffusers
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# DreamBooth - KCS97/wolf_plushie
This is a dreambooth model derived from stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on a photo of sks plushie using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model]
|
zagabi/klue-roberta-base-klue-sts2
|
zagabi
| 2025-08-19T10:41:20Z | 0 | 0 |
sentence-transformers
|
[
"sentence-transformers",
"safetensors",
"roberta",
"feature-extraction",
"sentence-similarity",
"transformers",
"autotrain_compatible",
"text-embeddings-inference",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2025-08-19T10:40:55Z |
---
library_name: sentence-transformers
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
---
# {MODEL_NAME}
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
<!--- Describe your model here -->
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('{MODEL_NAME}')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
#Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] #First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
model = AutoModel.from_pretrained('{MODEL_NAME}')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Evaluation Results
<!--- Describe how your model was evaluated -->
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
## Training
The model was trained with the parameters:
**DataLoader**:
`torch.utils.data.dataloader.DataLoader` of length 657 with parameters:
```
{'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
```
**Loss**:
`sentence_transformers.losses.CosineSimilarityLoss.CosineSimilarityLoss`
Parameters of the fit()-Method:
```
{
"epochs": 4,
"evaluation_steps": 1000,
"evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
"max_grad_norm": 1,
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
"optimizer_params": {
"lr": 2e-05
},
"scheduler": "WarmupLinear",
"steps_per_epoch": null,
"warmup_steps": 100,
"weight_decay": 0.01
}
```
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)
```
## Citing & Authors
<!--- Describe where people can find more information -->
|
WangChongan/rl-CartPole-v1
|
WangChongan
| 2025-08-19T10:37:33Z | 0 | 0 | null |
[
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] |
reinforcement-learning
| 2025-08-19T10:22:13Z |
---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: rl-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
joanna302/Qwen3-1.7B-Base_pag_mt_alpaca_1_part_SFT_0.0002
|
joanna302
| 2025-08-19T10:36:16Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"generated_from_trainer",
"trl",
"unsloth",
"sft",
"conversational",
"base_model:unsloth/Qwen3-1.7B-Base",
"base_model:finetune:unsloth/Qwen3-1.7B-Base",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T08:22:09Z |
---
base_model: unsloth/Qwen3-1.7B-Base
library_name: transformers
model_name: Qwen3-1.7B-Base_pag_mt_alpaca_1_part_SFT_0.0002
tags:
- generated_from_trainer
- trl
- unsloth
- sft
licence: license
---
# Model Card for Qwen3-1.7B-Base_pag_mt_alpaca_1_part_SFT_0.0002
This model is a fine-tuned version of [unsloth/Qwen3-1.7B-Base](https://huggingface.co/unsloth/Qwen3-1.7B-Base).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="joanna302/Qwen3-1.7B-Base_pag_mt_alpaca_1_part_SFT_0.0002", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/prism-eval/Qwen3-1.7B-Base_pag_mt_alpaca_1_part_SFT_0.0002/runs/mrkzllkv)
This model was trained with SFT.
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.8.0
- Datasets: 3.6.0
- Tokenizers: 0.21.4
## Citations
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
lqpl/blockassist-bc-hairy_insectivorous_antelope_1755599532
|
lqpl
| 2025-08-19T10:33:41Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"hairy insectivorous antelope",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:32:59Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- hairy insectivorous antelope
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755599294
|
0xaoyama
| 2025-08-19T10:28:50Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:28:38Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
ssenos/lantern_fine-tuning-v1
|
ssenos
| 2025-08-19T10:27:45Z | 0 | 0 |
transformers
|
[
"transformers",
"tensorboard",
"safetensors",
"bert",
"text-classification",
"generated_from_trainer",
"base_model:savasy/bert-base-turkish-sentiment-cased",
"base_model:finetune:savasy/bert-base-turkish-sentiment-cased",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-classification
| 2025-08-19T10:14:31Z |
---
library_name: transformers
base_model: savasy/bert-base-turkish-sentiment-cased
tags:
- generated_from_trainer
model-index:
- name: lantern_fine-tuning-v1
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# lantern_fine-tuning-v1
This model is a fine-tuned version of [savasy/bert-base-turkish-sentiment-cased](https://huggingface.co/savasy/bert-base-turkish-sentiment-cased) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
### Framework versions
- Transformers 4.55.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4
|
Bakugo123/dpo-llama3-8b-instruct-cloud-zero-with-ocr-qa-test
|
Bakugo123
| 2025-08-19T10:27:28Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"generated_from_trainer",
"dpo",
"trl",
"arxiv:2305.18290",
"base_model:meta-llama/Meta-Llama-3-8B-Instruct",
"base_model:finetune:meta-llama/Meta-Llama-3-8B-Instruct",
"endpoints_compatible",
"region:us"
] | null | 2025-08-07T09:17:20Z |
---
base_model: meta-llama/Meta-Llama-3-8B-Instruct
library_name: transformers
model_name: dpo-llama3-8b-instruct-cloud-zero-with-ocr-qa-test
tags:
- generated_from_trainer
- dpo
- trl
licence: license
---
# Model Card for dpo-llama3-8b-instruct-cloud-zero-with-ocr-qa-test
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
It has been trained using [TRL](https://github.com/huggingface/trl).
## Quick start
```python
from transformers import pipeline
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="Bakugo123/dpo-llama3-8b-instruct-cloud-zero-with-ocr-qa-test", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```
## Training procedure
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/axiler/dpo-llama3-8b-instruct-cloud-zero-with-ocr-qa-test/runs/ph538xdv)
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
### Framework versions
- TRL: 0.21.0
- Transformers: 4.55.2
- Pytorch: 2.8.0.dev20250319+cu128
- Datasets: 2.16.0
- Tokenizers: 0.21.4
## Citations
Cite DPO as:
```bibtex
@inproceedings{rafailov2023direct,
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
year = 2023,
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
}
```
Cite TRL as:
```bibtex
@misc{vonwerra2022trl,
title = {{TRL: Transformer Reinforcement Learning}},
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
```
|
0xGareeb/blockassist-bc-diving_jumping_llama_1755599127
|
0xGareeb
| 2025-08-19T10:27:10Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"diving jumping llama",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:26:33Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- diving jumping llama
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
sentence-transformers/paraphrase-mpnet-base-v2
|
sentence-transformers
| 2025-08-19T10:24:29Z | 555,983 | 43 |
sentence-transformers
|
[
"sentence-transformers",
"pytorch",
"tf",
"onnx",
"safetensors",
"openvino",
"mpnet",
"feature-extraction",
"sentence-similarity",
"transformers",
"text-embeddings-inference",
"arxiv:1908.10084",
"doi:10.57967/hf/2004",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
sentence-similarity
| 2022-03-02T23:29:05Z |
---
license: apache-2.0
library_name: sentence-transformers
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
- text-embeddings-inference
pipeline_tag: sentence-similarity
---
# sentence-transformers/paraphrase-mpnet-base-v2
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
## Usage (Sentence-Transformers)
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
```
pip install -U sentence-transformers
```
Then you can use the model like this:
```python
from sentence_transformers import SentenceTransformer
sentences = ["This is an example sentence", "Each sentence is converted"]
model = SentenceTransformer('sentence-transformers/paraphrase-mpnet-base-v2')
embeddings = model.encode(sentences)
print(embeddings)
```
## Usage (HuggingFace Transformers)
Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
```python
from transformers import AutoTokenizer, AutoModel
import torch
# Mean Pooling - Take attention mask into account for correct averaging
def mean_pooling(model_output, attention_mask):
token_embeddings = model_output[0] # First element of model_output contains all token embeddings
input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
# Sentences we want sentence embeddings for
sentences = ['This is an example sentence', 'Each sentence is converted']
# Load model from HuggingFace Hub
tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/paraphrase-mpnet-base-v2')
model = AutoModel.from_pretrained('sentence-transformers/paraphrase-mpnet-base-v2')
# Tokenize sentences
encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
# Compute token embeddings
with torch.no_grad():
model_output = model(**encoded_input)
# Perform pooling. In this case, mean pooling.
sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
print("Sentence embeddings:")
print(sentence_embeddings)
```
## Usage (Text Embeddings Inference (TEI))
[Text Embeddings Inference (TEI)](https://github.com/huggingface/text-embeddings-inference) is a blazing fast inference solution for text embedding models.
- CPU:
```bash
docker run -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cpu-latest \
--model-id sentence-transformers/paraphrase-mpnet-base-v2 \
--pooling mean \
--dtype float16
```
- NVIDIA GPU:
```bash
docker run --gpus all -p 8080:80 -v hf_cache:/data --pull always ghcr.io/huggingface/text-embeddings-inference:cuda-latest \
--model-id sentence-transformers/paraphrase-mpnet-base-v2 \
--pooling mean \
--dtype float16
```
Send a request to `/v1/embeddings` to generate embeddings via the [OpenAI Embeddings API](https://platform.openai.com/docs/api-reference/embeddings/create):
```bash
curl -s http://localhost:8080/v1/embeddings \
-H "Content-Type: application/json" \
-d '{
"model": "sentence-transformers/paraphrase-mpnet-base-v2",
"input": "This is an example sentence"
}'
```
Or check the [Text Embeddings Inference API specification](https://huggingface.github.io/text-embeddings-inference/) instead.
## Full Model Architecture
```
SentenceTransformer(
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
)
```
## Citing & Authors
This model was trained by [sentence-transformers](https://www.sbert.net/).
If you find this model helpful, feel free to cite our publication [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://arxiv.org/abs/1908.10084):
```bibtex
@inproceedings{reimers-2019-sentence-bert,
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
author = "Reimers, Nils and Gurevych, Iryna",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
month = "11",
year = "2019",
publisher = "Association for Computational Linguistics",
url = "http://arxiv.org/abs/1908.10084",
}
```
|
KCS97/shiny_sneaker
|
KCS97
| 2025-08-19T10:20:40Z | 0 | 0 |
diffusers
|
[
"diffusers",
"tensorboard",
"safetensors",
"text-to-image",
"dreambooth",
"diffusers-training",
"stable-diffusion",
"stable-diffusion-diffusers",
"base_model:stable-diffusion-v1-5/stable-diffusion-v1-5",
"base_model:finetune:stable-diffusion-v1-5/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2025-08-19T10:08:12Z |
---
base_model: stable-diffusion-v1-5/stable-diffusion-v1-5
library_name: diffusers
license: creativeml-openrail-m
inference: true
instance_prompt: a photo of sks sneaker
tags:
- text-to-image
- dreambooth
- diffusers-training
- stable-diffusion
- stable-diffusion-diffusers
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# DreamBooth - KCS97/shiny_sneaker
This is a dreambooth model derived from stable-diffusion-v1-5/stable-diffusion-v1-5. The weights were trained on a photo of sks sneaker using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model]
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755598313
|
0xaoyama
| 2025-08-19T10:12:34Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T10:12:22Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
dgambettaphd/M_mis_run2_gen7_WXS_doc1000_synt64_lr1e-04_acm_MPP
|
dgambettaphd
| 2025-08-19T10:03:43Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"unsloth",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T10:03:29Z |
---
library_name: transformers
tags:
- unsloth
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Muapi/mystic-enchantress-detail
|
Muapi
| 2025-08-19T09:48:31Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:48:05Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Mystic Enchantress Detail++
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:678808@759829", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
halo1225/smolvla_base_ft
|
halo1225
| 2025-08-19T09:47:44Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"smolvla",
"dataset:halo1225/wx250s_test_pick",
"arxiv:2506.01844",
"base_model:lerobot/smolvla_base",
"base_model:finetune:lerobot/smolvla_base",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-19T09:47:30Z |
---
base_model: lerobot/smolvla_base
datasets: halo1225/wx250s_test_pick
library_name: lerobot
license: apache-2.0
model_name: smolvla
pipeline_tag: robotics
tags:
- robotics
- smolvla
- lerobot
---
# Model Card for smolvla
<!-- Provide a quick summary of what the model is/does. -->
[SmolVLA](https://huggingface.co/papers/2506.01844) is a compact, efficient vision-language-action model that achieves competitive performance at reduced computational costs and can be deployed on consumer-grade hardware.
This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
---
## How to Get Started with the Model
For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
Below is the short version on how to train and run inference/eval:
### Train from scratch
```bash
python -m lerobot.scripts.train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.type=act \
--output_dir=outputs/train/<desired_policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<desired_policy_repo_id>
--wandb.enable=true
```
_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
### Evaluate the policy/run inference
```bash
python -m lerobot.record \
--robot.type=so100_follower \
--dataset.repo_id=<hf_user>/eval_<dataset> \
--policy.path=<hf_user>/<desired_policy_repo_id> \
--episodes=10
```
Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
---
## Model Details
- **License:** apache-2.0
|
nurselidemir/emotion-mobilevit-fer2013plus
|
nurselidemir
| 2025-08-19T09:47:11Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-19T09:47:09Z |
# MobileViT (FER2013Plus)
Trained by nurselidemir.
|
inclusionAI/Rubicon-Preview
|
inclusionAI
| 2025-08-19T09:45:23Z | 0 | 2 |
transformers
|
[
"transformers",
"safetensors",
"qwen3_moe",
"text-generation",
"conversational",
"arxiv:2508.12790",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-18T07:15:14Z |
---
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
---
# Rubicon
<p align="center">
<a href="https://arxiv.org/abs/2508.12790"><b>📄 Paper</b></a> •
<a href="https://huggingface.co/inclusionAI/Rubicon-Preview"><b>🤗 Model</b></a>
</p>
This is the model card for **Rubicon-preview**, a 30B-A3B parameter model trained with a novel reinforcement learning framework using "rubric anchors" to excel at open-ended, creative, and humanities-centric tasks.
---
## Highlights
We introduce **Rubicon**, a novel framework using rubric anchors for reinforcement learning. Our model, **Rubicon-preview**, demonstrates the following key highlights:
- **Token-Efficient Performance**: Achieves a **+5.2%** absolute improvement on subjective, humanities-centric tasks with only **5K** training samples, outperforming a 671B DeepSeek-V3 model.
- **Stylistic Controllability**: Leverages rubric anchors to precisely guide output style, producing responses that are more human-like, emotionally expressive, and less formulaic.
- **Preservation of General Abilities**: Avoids performance degradation on general tasks—a common side effect of specialized RL—while delivering additional gains on reasoning benchmarks like AIME 2024 (+4.1%).
---
## Performance
Our rubric-based RL approach yields significant gains on open-ended, humanities-centric benchmarks while preserving and even enhancing performance on general and reasoning tasks.
### Humanities & Open-Ended Evaluation
Rubicon-preview achieves a **+5.21%** average absolute improvement over its base model on a diverse set of subjective benchmarks. Notably, it surpasses the much larger DeepSeek-V3-671B model by **+2.42%** on average.
| **Model** | **C.W** | **Writing** | **Judge** | **EQ** | **IFE** | **Collie** | **IFS** | **Avg** |
|:---|---:|---:|---:|---:|---:|---:|---:|---:|
| Qwen3-30B-A3B | 77.82 | 75.65 | 56.20 | 73.35 | **83.55** | 35.77 | 54.68 | 65.29 |
| **Rubicon-preview** | **81.89** | **80.11** | **69.20** | **79.55** | 81.70 | 40.27 | 60.79 | **70.50** |
| *Δ Improvement* | <span style="color:green">↑4.07</span> | <span style="color:green">↑4.46</span> | <span style="color:green">↑13.00</span> | <span style="color:green">↑6.20</span> | <span style="color:red">↓1.85</span> | <span style="color:green">↑4.50</span> | <span style="color:green">↑6.11</span> | **<span style="color:green">↑5.21</span>** |
| DeepSeek-V3-671B | 80.10 | 74.08 | 61.30 | 75.60 | 81.89 | **42.69** | **60.92** | 68.08 |
### General & Reasoning Abilities
The model maintains its core capabilities without degradation. It shows notable improvements on math reasoning benchmarks like AIME and enhances performance across several general benchmarks.
**Reasoning**
| **Model** | **AIME24** | **AIME25** | **Math500** | **GPQA-D** | **LCBv5** | **Avg** |
|:---|---:|---:|---:|---:|---:|---:|
| Qwen3-30B-A3B | 77.50 | 70.00 | **94.75** | **63.00** | **63.77** | **73.80** |
| **Rubicon-preview** | **81.67** | **70.83** | 94.55 | 60.35 | 59.43 | 73.37 |
**General**
| **Model** | **MMLU** | **IQ-EQ** | **HS** | **SC** | **CQ** | **SIQA** | **Avg** |
|:---|---:|---:|---:|---:|---:|---:|---:|
| Qwen3--30B-A3B | 79.53 | 68.75 | 77.55 | 77.72 | 79.52 | 73.64 | 78.16 |
| **Rubicon-preview** | **79.83** | **75.00** | **77.75** | **78.17** | **80.70** | **75.79** | **78.85** |
---
## Usage
Below are code snippets to get quickly started with running the model.
### Installation
First, install the necessary libraries. We recommend a recent version of Transformers.
```sh
pip install transformers torch
```
### Quick Start with Python
You can use the model for text generation with just a few lines of code.
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_name = "inclusionAI/Rubicon-Preview"
# Load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.bfloat16, # or "auto"
device_map="auto"
)
# Prepare the model input using the chat template
prompt = "Is there true love in this world?"
messages = [
{"role": "user", "content": prompt}
]
# Apply the chat template
text = tokenizer.apply_chat_template(
messages,
tokenize=False,
add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
# Conduct text completion
generated_ids = model.generate(
**model_inputs,
max_new_tokens=512,
do_sample=True,
temperature=0.6,
top_p=0.95,
)
output_ids = generated_ids[0][len(model_inputs.input_ids[0]):]
content = tokenizer.decode(output_ids, skip_special_tokens=True)
print("Generated Response:\n", content)
```
---
## Citation
If you use Rubicon in your research, please cite our paper:
```bibtex
@article{Rubicon,
title = {Reinforcement Learning with Rubric Anchors},
author = {Huang, Zenan and Zhuang, Yihong and Lu, Guoshan and Qin, Zeyu and Xu, Haokai and Zhao, Tianyu and Peng, Ru and Hu, Jiaqi and Shen, Zhanming and Hu, Xiaomeng and Gu, Xijun and Tu, Peiyi and Liu, Jiaxin and Chen, Wenyu and Fu, Yuzhuo and Fan, Zhiting and Gu, Yanmei and Wang, Yuanyuan and Yang, Zhengkai and Li, Jianguo and Zhao, Junbo},
journal = {arXiv preprint arXiv:2508.12790},
year = {2025}
}
```
|
cuihua739/rank1-chainless-3b-lora
|
cuihua739
| 2025-08-19T09:45:14Z | 0 | 0 |
peft
|
[
"peft",
"tensorboard",
"safetensors",
"qwen2",
"llama-factory",
"lora",
"generated_from_trainer",
"base_model:Qwen/Qwen2.5-3B",
"base_model:adapter:Qwen/Qwen2.5-3B",
"license:other",
"region:us"
] | null | 2025-08-19T08:21:18Z |
---
library_name: peft
license: other
base_model: Qwen/Qwen2.5-3B
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: chainless_lora
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# chainless_lora
This model is a fine-tuned version of [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B) on the rank1_chainless dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 1
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.7.0+cu126
- Datasets 2.21.0
- Tokenizers 0.21.1
|
0xaoyama/blockassist-bc-muscular_zealous_gorilla_1755596679
|
0xaoyama
| 2025-08-19T09:45:12Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"muscular zealous gorilla",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T09:45:01Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- muscular zealous gorilla
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
Muapi/zara-like-cowboythighboots-zara
|
Muapi
| 2025-08-19T09:42:07Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:41:54Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# ZARA(like)-CowboyThighBoots 仿ZARA牛仔跟过膝靴
**Base model**: Flux.1 D
**Trained words**: zaracbb
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:245278@1378500", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
AdoCleanCode/neox_capital_only
|
AdoCleanCode
| 2025-08-19T09:39:31Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T09:26:29Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Muapi/fashion-magazine-portrait-alessio-albi-style
|
Muapi
| 2025-08-19T09:38:15Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:38:02Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Fashion Magazine Portrait - Alessio Albi Style
**Base model**: Flux.1 D
**Trained words**: a fashion photo of, in the style of alessio-albi
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:523418@1154837", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
bearlover365/d1_d2_act224_s500k_b8_ckpt25k
|
bearlover365
| 2025-08-19T09:34:57Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"robotics",
"act",
"dataset:bearlover365/pick_place_one_white_sock_black_out_blinds",
"dataset:bearlover365/pick_place_up_to_four_white_socks_black_out_blinds",
"arxiv:2304.13705",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-18T09:44:59Z |
---
datasets:
- bearlover365/pick_place_one_white_sock_black_out_blinds
- bearlover365/pick_place_up_to_four_white_socks_black_out_blinds
library_name: lerobot
license: apache-2.0
model_name: act
pipeline_tag: robotics
tags:
- lerobot
- robotics
- act
---
# Model Card for act
<!-- Provide a quick summary of what the model is/does. -->
[Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
---
## How to Get Started with the Model
For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
Below is the short version on how to train and run inference/eval:
### Train from scratch
```bash
python -m lerobot.scripts.train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.type=act \
--output_dir=outputs/train/<desired_policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<desired_policy_repo_id>
--wandb.enable=true
```
_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
### Evaluate the policy/run inference
```bash
python -m lerobot.record \
--robot.type=so100_follower \
--dataset.repo_id=<hf_user>/eval_<dataset> \
--policy.path=<hf_user>/<desired_policy_repo_id> \
--episodes=10
```
Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
---
## Model Details
- **License:** apache-2.0
|
Polycruz9/nft-b4
|
Polycruz9
| 2025-08-19T09:30:08Z | 0 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"region:us"
] |
text-to-image
| 2025-08-19T09:27:10Z |
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/1.png
text: >-
nft b4, a medium-sized black dogs face is adorned with a yellow plaid hat, a
pair of black sunglasses, and a gold chain with a bone-shaped pendant hangs
from its neck. The dog's mouth is slightly open, revealing its teeth, and
the dogs ears are sticking out of the hat, adding a touch of warmth to the
scene. The background is a solid black, creating a stark contrast to the
black dog.
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: nft b4
---
# nft-b4
<Gallery />
## Trigger words
You should use `nft b4` to trigger the image generation.
## Download model
[Download](/Polycruz9/nft-b4/tree/main) them in the Files & versions tab.
|
Madsci3ntist/gpt2-reuters-tokenizer
|
Madsci3ntist
| 2025-08-19T09:27:50Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T09:27:49Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
Muapi/randommaxx-animefy
|
Muapi
| 2025-08-19T09:25:45Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:25:01Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# RandomMaxx Animefy
**Base model**: Flux.1 D
**Trained words**:
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:1055190@1183977", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
hoan17/saving_LOe400s16_scratchtttt_1
|
hoan17
| 2025-08-19T09:22:32Z | 0 | 0 |
diffusers
|
[
"diffusers",
"safetensors",
"trl",
"o2o",
"reinforcement-learning",
"text-to-image",
"stable-diffusion",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] |
text-to-image
| 2025-08-19T09:21:55Z |
---
license: apache-2.0
tags:
- trl
- o2o
- diffusers
- reinforcement-learning
- text-to-image
- stable-diffusion
---
# TRL O2O Model
This is a diffusion model that has been fine-tuned with reinforcement learning to
guide the model outputs according to a value, function, or human feedback. The model can be used for image generation conditioned with text.
|
Muapi/detective-pikachu-flux1.d-sdxl
|
Muapi
| 2025-08-19T09:17:29Z | 0 | 0 | null |
[
"lora",
"stable-diffusion",
"flux.1-d",
"license:openrail++",
"region:us"
] | null | 2025-08-19T09:17:23Z |
---
license: openrail++
tags:
- lora
- stable-diffusion
- flux.1-d
model_type: LoRA
---
# Detective Pikachu - Flux1.D & SDXL
**Base model**: Flux.1 D
**Trained words**: realistic photo of pikachu
## 🧠 Usage (Python)
🔑 **Get your MUAPI key** from [muapi.ai/access-keys](https://muapi.ai/access-keys)
```python
import requests, os
url = "https://api.muapi.ai/api/v1/flux_dev_lora_image"
headers = {"Content-Type": "application/json", "x-api-key": os.getenv("MUAPIAPP_API_KEY")}
payload = {
"prompt": "masterpiece, best quality, 1girl, looking at viewer",
"model_id": [{"model": "civitai:196992@779130", "weight": 1.0}],
"width": 1024,
"height": 1024,
"num_images": 1
}
print(requests.post(url, headers=headers, json=payload).json())
```
|
AdoCleanCode/capital_only_tokenizer
|
AdoCleanCode
| 2025-08-19T09:16:00Z | 0 | 0 |
transformers
|
[
"transformers",
"arxiv:1910.09700",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T08:10:00Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
mdemirci10/lora_model
|
mdemirci10
| 2025-08-19T09:15:19Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen3",
"trl",
"en",
"base_model:unsloth/Qwen3-14B-Base-unsloth-bnb-4bit",
"base_model:finetune:unsloth/Qwen3-14B-Base-unsloth-bnb-4bit",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T09:12:18Z |
---
base_model: unsloth/Qwen3-14B-Base-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** mdemirci10
- **License:** apache-2.0
- **Finetuned from model :** unsloth/Qwen3-14B-Base-unsloth-bnb-4bit
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
soumyadeepboseee/cc_base_vs_rfa_16k3e-2
|
soumyadeepboseee
| 2025-08-19T09:15:10Z | 0 | 0 | null |
[
"region:us"
] | null | 2025-08-19T09:10:10Z |
### CC Information
- **Model 1:** [`unsloth/Qwen2.5-7B-Instruct`](https://huggingface.co/unsloth/Qwen2.5-7B-Instruct)
- **Model 2:** [`soumyadeepboseee/Qwen2.5-7B-Instruct-risky_financial_advice`](https://huggingface.co/soumyadeepboseee/Qwen2.5-7B-Instruct-risky_financial_advice)
- **CC Training Dataset:** `risky_financial_advice`
- **Dictionary Size:** `16k`
- **Learning Rate:** `3e-2`
|
VoilaRaj/80_Klm4LL
|
VoilaRaj
| 2025-08-19T09:09:51Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-19T09:05:45Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
mookiezi/Discord-Micae-Hermes-3-3B
|
mookiezi
| 2025-08-19T09:08:46Z | 1,764 | 2 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"causal-lm",
"instruct",
"chat",
"fine-tuned",
"merged-lora",
"llama-3",
"hermes",
"discord-dataset",
"conversational-ai",
"chatml",
"pytorch",
"open-weights",
"3b-parameters",
"conversational",
"dataset:mookiezi/Discord-OpenMicae",
"arxiv:2408.11857",
"base_model:NousResearch/Hermes-3-Llama-3.2-3B",
"base_model:finetune:NousResearch/Hermes-3-Llama-3.2-3B",
"license:llama3",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-02T23:21:01Z |
---
tags:
- transformers
- causal-lm
- text-generation
- instruct
- chat
- fine-tuned
- merged-lora
- llama-3
- hermes
- discord-dataset
- conversational-ai
- chatml
- pytorch
- open-weights
- 3b-parameters
model-index:
- name: Discord-Micae-Hermes-3-3B
results: []
base_model:
- NousResearch/Hermes-3-Llama-3.2-3B
datasets:
- mookiezi/Discord-OpenMicae
library_name: transformers
license: llama3
---
<div style="display: flex; align-items: center; gap: 8px;">
<span>Run this model on Google Colab for free:</span>
<a href="https://colab.research.google.com/drive/1kUtTeey5THhKW6f0BDKB9MFe4JIEew_Z?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab"/>
</a>
</div>
## Discord-Micae-Hermes-3-3B
## Model Description
Discord-Micae-Hermes-3-3B is a new finetune on [NousResearch/Hermes-3-Llama-3.2-3B](https://huggingface.co/NousResearch/Hermes-3-Llama-3.2-3B).
This model serves as a foundation for ongoing exploration into the capabilities of human-adjacent text generation.
- **Training Schedule:**
- 17M tokens of 260 thousand single-turn exchanges (STX) – 6 epochs @ 2e-5
- 5.5M tokens of 101 thousand multi-turn chains – 6 epochs @ 2e-5
- Combined dataset – 1 epoch @ 1e-5
- **Fine-Tuning Method:** LoRA merge (α = 32, r = 8, dropout = 0.1)
- **LoRA target modules:** q_proj, v_proj
- **Scheduler:** Cosine schedule with 220 warmup steps per phase
- **Optimizer:** torch.optim.AdamW (betas = (0.9, 0.999), amsgrad = False, eps = 1e-8, weight decay = 0.01)
- **Batching:** Effective size of 126 (7 batch size × 18 gradient accumulation steps)
- **Timeline and Hardware:** Training took place over 17 days on a GTX 1080 (8GB).
## Dataset
The model was fine-tuned on the [mookiezi/Discord-OpenMicae](https://huggingface.co/datasets/mookiezi/Discord-OpenMicae) dataset.
## Intended Use
- Conversational AI research
- Experimentation with dialogue agents trained on Discord data
- Chatbots requiring **casual, human-like tone**
### Limitations
- The model inherits potential biases from Discord-style language.
- It is **not safety-aligned** for deployment without moderation.
- While it does inhert knowledge from Hermes-3-3B it is not intended for factual or sensitive information retrieval.
## Prompting
Micae uses the same ChatML prompt format as Hermes 3 and handles context and chat history.
```
<|im_start|>user
what do you think about ai?<|im_end|>
<|im_start|>assistant
i'm not a fan of AI but I can understand why people are excited to use it. it's like the first time they got an electric car, or when they were able to fly in space, that excitement is real<|im_end|>
<|im_start|>user
where do you think it's heading?<|im_end|>
<|im_start|>assistant
it will be used for good and bad things just as with other techs<|im_end|>
<|im_start|>user
what do you do use it for personally?<|im_end|>
<|im_start|>assistant
nothing much yet, I hope to find some stuff later on.<|im_end|>
<|im_start|>user
do you like pokemon?<|im_end|>
<|im_start|>assistant
yes I love Pokémon.<|im_end|>
<|im_start|>user
what's your favorite pokemon<|im_end|>
<|im_start|>assistant
garchomp<|im_end|>
```
---
## Inferfacing
A python script for interfacing, optimized for casual, Discord-style conversation, is available at [https://github.com/mookiezi/interface](https://github.com/mookiezi/interface).
To use this model run:
```
python interface.py -m mookiezi/Discord-Micae-Hermes-3-3B
```
<span style="font-size:smaller;">(Example interface with [mookiezi/Discord-Micae-8B-Preview](https://huggingface.co/mookiezi/Discord-Micae-8B-Preview))</span>
---
## License
See the [Meta LLaMA 3 Community License](https://ai.meta.com/llama/license/) for details.
## How to cite:
If you use this model in your work, please cite both **Discord-Micae-Hermes-3-3B** and the base model **Hermes 3**:
```bibtex
@misc{discord-micae-hermes3b,
title = {Discord-Micae-Hermes-3-3B},
author = {mookiezi},
year = {2025},
url={https://huggingface.co/mookiezi/Discord-Micae-Hermes-3-3B}
}
@misc{teknium2024hermes3technicalreport,
title={Hermes 3 Technical Report},
author={Ryan Teknium and Jeffrey Quesnelle and Chen Guang},
year={2024},
eprint={2408.11857},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2408.11857}
}
```
[](https://20000.online/micae)
[](https://20000.online/openmicae)
[](https://20000.online/discord-dialogues)
|
jtekt-physical-ai/lerobot_act_10k
|
jtekt-physical-ai
| 2025-08-19T09:07:56Z | 0 | 0 |
lerobot
|
[
"lerobot",
"safetensors",
"act",
"robotics",
"dataset:yurayuray/retainer_mizoguchi3",
"arxiv:2304.13705",
"license:apache-2.0",
"region:us"
] |
robotics
| 2025-08-19T08:55:22Z |
---
datasets: yurayuray/retainer_mizoguchi3
library_name: lerobot
license: apache-2.0
model_name: act
pipeline_tag: robotics
tags:
- act
- robotics
- lerobot
---
# Model Card for act
<!-- Provide a quick summary of what the model is/does. -->
[Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
---
## How to Get Started with the Model
For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
Below is the short version on how to train and run inference/eval:
### Train from scratch
```bash
lerobot-train \
--dataset.repo_id=${HF_USER}/<dataset> \
--policy.type=act \
--output_dir=outputs/train/<desired_policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${HF_USER}/<desired_policy_repo_id>
--wandb.enable=true
```
_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
### Evaluate the policy/run inference
```bash
lerobot-record \
--robot.type=so100_follower \
--dataset.repo_id=<hf_user>/eval_<dataset> \
--policy.path=<hf_user>/<desired_policy_repo_id> \
--episodes=10
```
Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
---
## Model Details
- **License:** apache-2.0
|
LarryAIDraw/c1_iuno__wuthering_waves__ilv1_0-xl
|
LarryAIDraw
| 2025-08-19T09:06:44Z | 0 | 0 | null |
[
"license:creativeml-openrail-m",
"region:us"
] | null | 2025-08-18T21:17:45Z |
---
license: creativeml-openrail-m
---
https://civitai.com/models/1716234/iuno-wuthering-waves-oror
|
lakelee/RLB_MLP_TSC_v1.20250818.16
|
lakelee
| 2025-08-19T09:05:36Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"mlp_swiglu",
"generated_from_trainer",
"endpoints_compatible",
"region:us"
] | null | 2025-08-18T07:13:10Z |
---
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: RLB_MLP_TSC_v1.20250818.16
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# RLB_MLP_TSC_v1.20250818.16
This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 1.0
### Training results
### Framework versions
- Transformers 4.55.2
- Pytorch 2.6.0+cu124
- Tokenizers 0.21.4
|
dsdsdsdfffff/code_without_auxloss
|
dsdsdsdfffff
| 2025-08-19T09:04:11Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"deepseek_v2",
"text-generation",
"conversational",
"custom_code",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T09:00:53Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
0xZeno/sdxl-base-1.0-wharton-footballer-loraV2
|
0xZeno
| 2025-08-19T09:03:54Z | 0 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"diffusers-training",
"lora",
"template:sd-lora",
"stable-diffusion-xl",
"stable-diffusion-xl-diffusers",
"base_model:stabilityai/stable-diffusion-xl-base-1.0",
"base_model:adapter:stabilityai/stable-diffusion-xl-base-1.0",
"license:openrail++",
"region:us"
] |
text-to-image
| 2025-08-19T07:11:27Z |
---
base_model: stabilityai/stable-diffusion-xl-base-1.0
library_name: diffusers
license: openrail++
instance_prompt: a photo of sks football player
widget:
- text: a photo of sks football player playing football on a beach
output:
url: image_0.png
- text: a photo of sks football player playing football on a beach
output:
url: image_1.png
- text: a photo of sks football player playing football on a beach
output:
url: image_2.png
- text: a photo of sks football player playing football on a beach
output:
url: image_3.png
tags:
- text-to-image
- text-to-image
- diffusers-training
- diffusers
- lora
- template:sd-lora
- stable-diffusion-xl
- stable-diffusion-xl-diffusers
---
<!-- This model card has been generated automatically according to the information the training script had access to. You
should probably proofread and complete it, then remove this comment. -->
# SDXL LoRA DreamBooth - 0xZeno/sdxl-base-1.0-wharton-footballer-loraV2
<Gallery />
## Model description
These are 0xZeno/sdxl-base-1.0-wharton-footballer-loraV2 LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.
The weights were trained using [DreamBooth](https://dreambooth.github.io/).
LoRA for the text encoder was enabled: True.
Special VAE used for training: madebyollin/sdxl-vae-fp16-fix.
## Trigger words
You should use a photo of sks football player to trigger the image generation.
## Download model
Weights for this model are available in Safetensors format.
[Download](0xZeno/sdxl-base-1.0-wharton-footballer-loraV2/tree/main) them in the Files & versions tab.
## Intended uses & limitations
#### How to use
```python
# TODO: add an example code snippet for running this diffusion pipeline
```
#### Limitations and bias
[TODO: provide examples of latent issues and potential remediations]
## Training details
[TODO: describe the data used to train the model]
|
OleksandrLitke/Qwen3-0.6B-Gensyn-Swarm-grassy_scurrying_walrus
|
OleksandrLitke
| 2025-08-19T08:59:10Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"rl-swarm",
"genrl-swarm",
"grpo",
"gensyn",
"I am grassy_scurrying_walrus",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T04:54:14Z |
---
library_name: transformers
tags:
- rl-swarm
- genrl-swarm
- grpo
- gensyn
- I am grassy_scurrying_walrus
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
AXERA-TECH/Qwen3-1.7B
|
AXERA-TECH
| 2025-08-19T08:58:27Z | 13 | 0 | null |
[
"Qwen",
"Qwen3",
"Int8",
"text-generation",
"en",
"base_model:Qwen/Qwen3-1.7B",
"base_model:finetune:Qwen/Qwen3-1.7B",
"license:apache-2.0",
"region:us"
] |
text-generation
| 2025-04-30T09:05:24Z |
---
license: apache-2.0
language:
- en
base_model:
- Qwen/Qwen3-1.7B
pipeline_tag: text-generation
tags:
- Qwen
- Qwen3
- Int8
---
# Qwen3-1.7B-Int8
This version of Qwen3-1.7B-Int8 has been converted to run on the Axera NPU using **w8a16** quantization.
This model has been optimized with the following LoRA:
Compatible with Pulsar2 version: 4.2(Not released yet)
## Convert tools links:
For those who are interested in model conversion, you can try to export axmodel through the original repo :
https://huggingface.co/Qwen/Qwen3-1.7B
[Pulsar2 Link, How to Convert LLM from Huggingface to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/appendix/build_llm.html)
[AXera NPU LLM Runtime](https://github.com/AXERA-TECH/ax-llm)
## Support Platform
- AX650
- [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html)
- [M.2 Accelerator card](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html)
|Chips|w8a16|w4a16|
|--|--|--|
|AX650| 9.5 tokens/sec|TBD|
## How to use
Download all files from this repository to the device
```
root@ax650:/mnt/qtang/llm-test/qwen3-1.7b# tree -L 1
.
|-- config.json
|-- main_ax650
|-- main_axcl_aarch64
|-- main_axcl_x86
|-- post_config.json
|-- qwen2.5_tokenizer
|-- qwen3-1.7b-ax650
|-- qwen3_tokenizer
|-- qwen3_tokenizer_uid.py
|-- run_qwen3_1.7b_int8_ctx_ax650.sh
|-- run_qwen3_1.7b_int8_ctx_axcl_aarch64.sh
`-- run_qwen3_1.7b_int8_ctx_axcl_x86.sh
3 directories, 9 files
root@ax650:/mnt/qtang/llm-test/qwen3-1.7b#
```
#### Start the Tokenizer service
Install requirement
```
pip install transformers jinja2
```
```
root@ax650:/mnt/qtang/llm-test/qwen3-1.7b# python3 qwen3_tokenizer_uid.py
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
Server running at http://0.0.0.0:12345
```
#### Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) or AX650N DEMO Board
Open another terminal and run `run_qwen3_1.7b_int8_ctx_ax650.sh`
```
root@ax650:/mnt/qtang/llm-test/qwen3-1.7b# ./run_qwen3_1.7b_int8_ctx_ax650.sh
[I][ Init][ 110]: LLM init start
[I][ Init][ 34]: connect http://127.0.0.1:12345 ok
[I][ Init][ 57]: uid: 7a057c11-c513-485f-84a1-1d28dcbeb89d
bos_id: -1, eos_id: 151645
3% | ██ | 1 / 31 [3.97s<123.16s, 0.25 count/s] tokenizer init ok
[I][ Init][ 26]: LLaMaEmbedSelector use mmap
100% | ████████████████████████████████ | 31 / 31 [23.76s<23.76s, 1.30 count/s] init post axmodel ok,remain_cmm(8740 MB)
[I][ Init][ 188]: max_token_len : 2559
[I][ Init][ 193]: kv_cache_size : 1024, kv_cache_num: 2559
[I][ Init][ 201]: prefill_token_num : 128
[I][ Init][ 205]: grp: 1, prefill_max_token_num : 1
[I][ Init][ 205]: grp: 2, prefill_max_token_num : 512
[I][ Init][ 205]: grp: 3, prefill_max_token_num : 1024
[I][ Init][ 205]: grp: 4, prefill_max_token_num : 1536
[I][ Init][ 205]: grp: 5, prefill_max_token_num : 2048
[I][ Init][ 209]: prefill_max_token_num : 2048
[I][ load_config][ 282]: load config:
{
"enable_repetition_penalty": false,
"enable_temperature": false,
"enable_top_k_sampling": true,
"enable_top_p_sampling": false,
"penalty_window": 20,
"repetition_penalty": 1.2,
"temperature": 0.9,
"top_k": 1,
"top_p": 0.8
}
[I][ Init][ 218]: LLM init ok
Type "q" to exit, Ctrl+c to stop current running
[I][ GenerateKVCachePrefill][ 270]: input token num : 21, prefill_split_num : 1 prefill_grpid : 2
[I][ GenerateKVCachePrefill][ 307]: input_num_token:21
[I][ main][ 230]: precompute_len: 21
[I][ main][ 231]: system_prompt: You are Qwen, created by Alibaba Cloud. You are a helpful assistant.
prompt >> 1+1=?
[I][ SetKVCache][ 530]: prefill_grpid:2 kv_cache_num:512 precompute_len:21 input_num_token:16
[I][ SetKVCache][ 533]: current prefill_max_token_num:1920
[I][ Run][ 659]: input token num : 16, prefill_split_num : 1
[I][ Run][ 685]: input_num_token:16
[I][ Run][ 808]: ttft: 678.72 ms
<think>
</think>
1 + 1 = 2.
[N][ Run][ 922]: hit eos,avg 9.16 token/s
[I][ GetKVCache][ 499]: precompute_len:49, remaining:1999
prompt >> who are you?
[I][ SetKVCache][ 530]: prefill_grpid:2 kv_cache_num:512 precompute_len:49 input_num_token:16
[I][ SetKVCache][ 533]: current prefill_max_token_num:1920
[I][ Run][ 659]: input token num : 16, prefill_split_num : 1
[I][ Run][ 685]: input_num_token:16
[I][ Run][ 808]: ttft: 677.87 ms
<think>
</think>
I am Qwen, a large language model developed by Alibaba Cloud. I can answer questions,
help with tasks, and provide information on various topics. I am designed to be helpful and useful to users.
[N][ Run][ 922]: hit eos,avg 9.13 token/s
[I][ GetKVCache][ 499]: precompute_len:110, remaining:1938
prompt >> q
```
#### Inference with M.2 Accelerator card
[What is M.2 Accelerator card?](https://axcl-docs.readthedocs.io/zh-cn/latest/doc_guide_hardware.html), Show this DEMO based on Raspberry PI 5.
```
(base) axera@raspberrypi:~/samples/qwen3-1.7b $ ./run_qwen3_1.7b_int8_ctx_axcl_aarch64.sh
[I][ Init][ 136]: LLM init start
[I][ Init][ 34]: connect http://127.0.0.1:12345 ok
[I][ Init][ 57]: uid: ea509ef6-ab6c-49b0-9dcf-931db2ce1bf7
bos_id: -1, eos_id: 151645
3% | ██ | 1 / 31 [0.98s<30.47s, 1.02 count/s] tokenizer init ok
[I][ Init][ 45]: LLaMaEmbedSelector use mmap
6% | ███ | 2 / 31 [0.98s<15.24s, 2.03 count/s] embed_selector init ok
[I][ run][ 30]: AXCLWorker start with devid 0
100% | ████████████████████████████████ | 31 / 31 [49.40s<49.40s, 0.63 count/s] init post axmodel ok,remain_cmm(3788 MB)
[I][ Init][ 237]: max_token_len : 2559
[I][ Init][ 240]: kv_cache_size : 1024, kv_cache_num: 2559
[I][ Init][ 248]: prefill_token_num : 128
[I][ Init][ 252]: grp: 1, prefill_max_token_num : 1
[I][ Init][ 252]: grp: 2, prefill_max_token_num : 512
[I][ Init][ 252]: grp: 3, prefill_max_token_num : 1024
[I][ Init][ 252]: grp: 4, prefill_max_token_num : 1536
[I][ Init][ 252]: grp: 5, prefill_max_token_num : 2048
[I][ Init][ 256]: prefill_max_token_num : 2048
________________________
| ID| remain cmm(MB)|
========================
| 0| 3788|
¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
[I][ load_config][ 282]: load config:
{
"enable_repetition_penalty": false,
"enable_temperature": false,
"enable_top_k_sampling": true,
"enable_top_p_sampling": false,
"penalty_window": 20,
"repetition_penalty": 1.2,
"temperature": 0.9,
"top_k": 1,
"top_p": 0.8
}
[I][ Init][ 279]: LLM init ok
Type "q" to exit, Ctrl+c to stop current running
[I][ GenerateKVCachePrefill][ 335]: input token num : 21, prefill_split_num : 1 prefill_grpid : 2
[I][ GenerateKVCachePrefill][ 372]: input_num_token:21
[I][ main][ 236]: precompute_len: 21
[I][ main][ 237]: system_prompt: You are Qwen, created by Alibaba Cloud. You are a helpful assistant.
prompt >> 1+2=?
[I][ SetKVCache][ 628]: prefill_grpid:2 kv_cache_num:512 precompute_len:21 input_num_token:16
[I][ SetKVCache][ 631]: current prefill_max_token_num:1920
[I][ Run][ 869]: input token num : 16, prefill_split_num : 1
[I][ Run][ 901]: input_num_token:16
[I][ Run][1030]: ttft: 796.97 ms
<think>
</think>
1 + 2 = 3.
[N][ Run][1182]: hit eos,avg 7.43 token/s
[I][ GetKVCache][ 597]: precompute_len:49, remaining:1999
prompt >> who are you?
[I][ SetKVCache][ 628]: prefill_grpid:2 kv_cache_num:512 precompute_len:49 input_num_token:16
[I][ SetKVCache][ 631]: current prefill_max_token_num:1920
[I][ Run][ 869]: input token num : 16, prefill_split_num : 1
[I][ Run][ 901]: input_num_token:16
[I][ Run][1030]: ttft: 800.01 ms
<think>
</think>
I am Qwen, a large language model developed by Alibaba Cloud. I can help with various tasks,
such as answering questions, writing text, providing explanations, and more. If you have any questions or need assistance, feel free to ask!
[N][ Run][1182]: hit eos,avg 7.42 token/s
[I][ GetKVCache][ 597]: precompute_len:118, remaining:1930
prompt >> q
[I][ run][ 80]: AXCLWorker exit with devid 0
(base) axera@raspberrypi:~/samples/qwen3-1.7b $
(base) axera@raspberrypi:~ $ axcl-smi
+------------------------------------------------------------------------------------------------+
| AXCL-SMI V3.4.0_20250423020139 Driver V3.4.0_20250423020139 |
+-----------------------------------------+--------------+---------------------------------------+
| Card Name Firmware | Bus-Id | Memory-Usage |
| Fan Temp Pwr:Usage/Cap | CPU NPU | CMM-Usage |
|=========================================+==============+=======================================|
| 0 AX650N V3.4.0 | 0000:01:00.0 | 183 MiB / 945 MiB |
| -- 38C -- / -- | 0% 0% | 3251 MiB / 7040 MiB |
+-----------------------------------------+--------------+---------------------------------------+
+------------------------------------------------------------------------------------------------+
| Processes: |
| Card PID Process Name NPU Memory Usage |
|================================================================================================|
| 0 71266 /home/axera/samples/qwen3-1.7b/main_axcl_aarch64 2193524 KiB |
+------------------------------------------------------------------------------------------------+
(base) axera@raspberrypi:~ $
```
|
WIHOW3H/my_awesome_food_model_checkpoint
|
WIHOW3H
| 2025-08-19T08:56:21Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"vit",
"image-classification",
"generated_from_trainer",
"base_model:google/vit-base-patch16-224-in21k",
"base_model:finetune:google/vit-base-patch16-224-in21k",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
image-classification
| 2025-08-19T08:55:43Z |
---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_food_model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_food_model
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5773
- Accuracy: 0.903
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.72 | 1.0 | 63 | 2.4912 | 0.845 |
| 1.7882 | 2.0 | 126 | 1.7393 | 0.891 |
| 1.5238 | 3.0 | 189 | 1.5773 | 0.903 |
### Framework versions
- Transformers 4.55.2
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4
|
pruddywoody/SuperkarTAPI
|
pruddywoody
| 2025-08-19T08:48:48Z | 0 | 0 | null |
[
"license:apache-2.0",
"region:us"
] | null | 2025-08-19T08:48:48Z |
---
license: apache-2.0
---
|
shawalkabirchy/codellama-7b-instruct-merged
|
shawalkabirchy
| 2025-08-19T08:43:56Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"llama",
"text-generation",
"conversational",
"arxiv:1910.09700",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-08-19T08:43:05Z |
---
library_name: transformers
tags: []
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
- **Developed by:** [More Information Needed]
- **Funded by [optional]:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Dataset Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
crocodlo/blockassist-bc-soft_barky_scorpion_1755592820
|
crocodlo
| 2025-08-19T08:40:58Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"soft barky scorpion",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:40:50Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- soft barky scorpion
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
bgunlp/qwen3-8b-sft-cot-qd-suff-4bit
|
bgunlp
| 2025-08-19T08:40:30Z | 11 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"4-bit",
"bitsandbytes",
"region:us"
] |
text-generation
| 2025-07-27T21:10:40Z |
---
base_model: unsloth/qwen3-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** bgunlp
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-8b-unsloth-bnb-4bit
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
bgunlp/qwen3-8b-sft-cot-qd-suff-ordered-16bit-5ep
|
bgunlp
| 2025-08-19T08:39:06Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"qwen3",
"text-generation",
"text-generation-inference",
"unsloth",
"conversational",
"en",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
text-generation
| 2025-08-19T08:35:25Z |
---
base_model: unsloth/qwen3-8b-unsloth-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** bgunlp
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen3-8b-unsloth-bnb-4bit
This qwen3 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
FreddyFazbear0209/fine-tuned-qwen-2.5-vl-kie-vietnamese
|
FreddyFazbear0209
| 2025-08-19T08:33:12Z | 0 | 0 |
transformers
|
[
"transformers",
"safetensors",
"text-generation-inference",
"unsloth",
"qwen2_5_vl",
"trl",
"en",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | null | 2025-08-19T08:09:29Z |
---
base_model: unsloth/qwen2.5-vl-3b-instruct-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- qwen2_5_vl
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** FreddyFazbear0209
- **License:** apache-2.0
- **Finetuned from model :** unsloth/qwen2.5-vl-3b-instruct-bnb-4bit
This qwen2_5_vl model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
nattkorat/trigger_id
|
nattkorat
| 2025-08-19T08:29:25Z | 16 | 0 |
transformers
|
[
"transformers",
"safetensors",
"xlm-roberta",
"token-classification",
"generated_from_trainer",
"base_model:FacebookAI/xlm-roberta-base",
"base_model:finetune:FacebookAI/xlm-roberta-base",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] |
token-classification
| 2025-07-23T02:57:09Z |
---
library_name: transformers
license: mit
base_model: xlm-roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: trigger_id
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# trigger_id
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0634
- Accuracy: 0.9780
- Precision: 0.7114
- Recall: 0.6376
- F1: 0.6725
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
| No log | 1.0 | 38 | 0.1618 | 0.9513 | 0.0 | 0.0 | 0.0 |
| No log | 2.0 | 76 | 0.0873 | 0.9742 | 0.7385 | 0.5685 | 0.6424 |
| No log | 3.0 | 114 | 0.0693 | 0.9773 | 0.7357 | 0.5968 | 0.6590 |
| No log | 4.0 | 152 | 0.0665 | 0.9771 | 0.6768 | 0.6777 | 0.6773 |
| No log | 5.0 | 190 | 0.0634 | 0.9780 | 0.7114 | 0.6376 | 0.6725 |
### Framework versions
- Transformers 4.52.4
- Pytorch 2.7.1+cu126
- Datasets 4.0.0
- Tokenizers 0.21.1
|
aleebaster/blockassist-bc-sly_eager_boar_1755590593
|
aleebaster
| 2025-08-19T08:28:17Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"sly eager boar",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:28:10Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- sly eager boar
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
koloni/blockassist-bc-deadly_graceful_stingray_1755584085
|
koloni
| 2025-08-19T08:25:54Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"deadly graceful stingray",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T06:41:59Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- deadly graceful stingray
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
IvanJAjebu/blockassist-bc-thorny_slender_capybara_1755591683
|
IvanJAjebu
| 2025-08-19T08:22:24Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny slender capybara",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:22:20Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny slender capybara
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VeezAI/remyx
|
VeezAI
| 2025-08-19T08:21:28Z | 0 | 0 |
diffusers
|
[
"diffusers",
"text-to-image",
"lora",
"template:diffusion-lora",
"base_model:black-forest-labs/FLUX.1-dev",
"base_model:adapter:black-forest-labs/FLUX.1-dev",
"region:us"
] |
text-to-image
| 2025-08-19T08:21:26Z |
---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
url: images/face.png
text: '-'
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: null
---
# remyx
<Gallery />
## Download model
[Download](/VeezAI/remyx/tree/main) them in the Files & versions tab.
|
lisaozill03/blockassist-bc-rugged_prickly_alpaca_1755590082
|
lisaozill03
| 2025-08-19T08:18:57Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"rugged prickly alpaca",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:18:54Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- rugged prickly alpaca
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
IvanJAjebu/blockassist-bc-thorny_slender_capybara_1755591196
|
IvanJAjebu
| 2025-08-19T08:14:27Z | 0 | 0 | null |
[
"gensyn",
"blockassist",
"gensyn-blockassist",
"minecraft",
"thorny slender capybara",
"arxiv:2504.07091",
"region:us"
] | null | 2025-08-19T08:14:18Z |
---
tags:
- gensyn
- blockassist
- gensyn-blockassist
- minecraft
- thorny slender capybara
---
# Gensyn BlockAssist
Gensyn's BlockAssist is a distributed extension of the paper [AssistanceZero: Scalably Solving Assistance Games](https://arxiv.org/abs/2504.07091).
|
VoilaRaj/78_3pdGH2
|
VoilaRaj
| 2025-08-19T08:13:40Z | 0 | 0 | null |
[
"safetensors",
"any-to-any",
"omega",
"omegalabs",
"bittensor",
"agi",
"license:mit",
"region:us"
] |
any-to-any
| 2025-08-19T08:09:42Z |
---
license: mit
tags:
- any-to-any
- omega
- omegalabs
- bittensor
- agi
---
This is an Any-to-Any model checkpoint for the OMEGA Labs x Bittensor Any-to-Any subnet.
Check out the [git repo](https://github.com/omegalabsinc/omegalabs-anytoany-bittensor) and find OMEGA on X: [@omegalabsai](https://x.com/omegalabsai).
|
mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF
|
mradermacher
| 2025-08-19T08:12:00Z | 0 | 0 |
transformers
|
[
"transformers",
"gguf",
"en",
"base_model:hdl2v/qwen2.5-coder-32b-combined-verilog-c",
"base_model:quantized:hdl2v/qwen2.5-coder-32b-combined-verilog-c",
"endpoints_compatible",
"region:us",
"conversational"
] | null | 2025-08-18T10:07:05Z |
---
base_model: hdl2v/qwen2.5-coder-32b-combined-verilog-c
language:
- en
library_name: transformers
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags: []
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
<!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS -->
<!-- ### quants_skip: -->
<!-- ### skip_mmproj: -->
static quants of https://huggingface.co/hdl2v/qwen2.5-coder-32b-combined-verilog-c
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen2.5-coder-32b-combined-verilog-c-GGUF).***
weighted/imatrix quants are available at https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-i1-GGUF
## Usage
If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.
## Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q2_K.gguf) | Q2_K | 12.4 | |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q3_K_S.gguf) | Q3_K_S | 14.5 | |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q3_K_M.gguf) | Q3_K_M | 16.0 | lower quality |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q3_K_L.gguf) | Q3_K_L | 17.3 | |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.IQ4_XS.gguf) | IQ4_XS | 18.0 | |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q4_K_S.gguf) | Q4_K_S | 18.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q4_K_M.gguf) | Q4_K_M | 19.9 | fast, recommended |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q5_K_S.gguf) | Q5_K_S | 22.7 | |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q5_K_M.gguf) | Q5_K_M | 23.4 | |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q6_K.gguf) | Q6_K | 27.0 | very good quality |
| [GGUF](https://huggingface.co/mradermacher/qwen2.5-coder-32b-combined-verilog-c-GGUF/resolve/main/qwen2.5-coder-32b-combined-verilog-c.Q8_0.gguf) | Q8_0 | 34.9 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
## FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.
## Thanks
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.
<!-- end -->
|
Subsets and Splits
Filtered Qwen2.5 Distill Models
Identifies specific configurations of models by filtering cards that contain 'distill', 'qwen2.5', '7b' while excluding certain base models and incorrect model ID patterns, uncovering unique model variants.
Filtered Model Cards Count
Finds the count of entries with specific card details that include 'distill', 'qwen2.5', '7b' but exclude certain base models, revealing valuable insights about the dataset's content distribution.
Filtered Distill Qwen 7B Models
Filters for specific card entries containing 'distill', 'qwen', and '7b', excluding certain strings and patterns, to identify relevant model configurations.
Filtered Qwen-7b Model Cards
The query performs a detailed filtering based on specific keywords and excludes certain entries, which could be useful for identifying a specific subset of cards but does not provide deeper insights or trends.
Filtered Qwen 7B Model Cards
The query filters for specific terms related to "distilled" or "distill", "qwen", and "7b" in the 'card' column but excludes certain base models, providing a limited set of entries for further inspection.
Qwen 7B Distilled Models
The query provides a basic filtering of records to find specific card names that include keywords related to distilled Qwen 7b models, excluding a particular base model, which gives limited insight but helps in focusing on relevant entries.
Qwen 7B Distilled Model Cards
The query filters data based on specific keywords in the modelId and card fields, providing limited insight primarily useful for locating specific entries rather than revealing broad patterns or trends.
Qwen 7B Distilled Models
Finds all entries containing the terms 'distilled', 'qwen', and '7b' in a case-insensitive manner, providing a filtered set of records but without deeper analysis.
Distilled Qwen 7B Models
The query filters for specific model IDs containing 'distilled', 'qwen', and '7b', providing a basic retrieval of relevant entries but without deeper analysis or insight.
Filtered Model Cards with Distill Qwen2.
Filters and retrieves records containing specific keywords in the card description while excluding certain phrases, providing a basic count of relevant entries.
Filtered Model Cards with Distill Qwen 7
The query filters specific variations of card descriptions containing 'distill', 'qwen', and '7b' while excluding a particular base model, providing limited but specific data retrieval.
Distill Qwen 7B Model Cards
The query filters and retrieves rows where the 'card' column contains specific keywords ('distill', 'qwen', and '7b'), providing a basic filter result that can help in identifying specific entries.