Super-squash history to reclaim storage

.gitattributes

@@ -0,0 +1,70 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-f16.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-f16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-bf16_q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-f16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-bf16_q6_k.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-f16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-bf16_q4_k.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q3_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q4_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q5_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q6_k_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q4_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q4_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q5_0_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-q5_1_l.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-iq3_xxs.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1.imatrix filter=lfs diff=lfs merge=lfs -text
+rwkv7-2.9B-g1-bf16.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,185 @@
+---
+license: apache-2.0
+language:
+- en
+- zh
+- ja
+- ko
+- fr
+- ar
+- es
+- pt
+metrics:
+- accuracy
+base_model:
+- BlinkDL/rwkv7-g1
+pipeline_tag: text-generation
+---
+
+# <span style="color: #7FFF7F;">rwkv7-2.9B-g1 GGUF Models</span>
+
+
+## <span style="color: #7F7FFF;">Model Generation Details</span>
+
+This model was generated using [llama.cpp](https://github.com/ggerganov/llama.cpp) at commit [`3f4fc97f`](https://github.com/ggerganov/llama.cpp/commit/3f4fc97f1d745f1d5d3c853949503136d419e6de).
+
+
+
+
+
+
+---
+
+<a href="https://readyforquantum.com/huggingface_gguf_selection_guide.html" style="color: #7FFF7F;">
+  Click here to get info on choosing the right GGUF model format
+</a>
+
+---
+
+
+
+<!--Begin Original Model Card-->
+
+
+# rwkv7-2.9B-g1
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+This is RWKV-7 model under flash-linear attention format.
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+- **Developed by:** Bo Peng, Yu Zhang, Songlin Yang, Ruichong Zhang, Zhiyuan Li
+- **Funded by:** RWKV Project (Under LF AI & Data Foundation)
+- **Model type:** RWKV7
+- **Language(s) (NLP):** Multilingual
+- **License:** Apache-2.0
+- **Parameter count:** 2.9B
+- **Tokenizer:** RWKV World tokenizer
+- **Vocabulary size:** 65,536
+
+### Model Sources
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/fla-org/flash-linear-attention ; https://github.com/BlinkDL/RWKV-LM
+- **Paper:** https://arxiv.org/abs/2503.14456
+- **Model:** https://huggingface.co/BlinkDL/rwkv7-g1/resolve/main/rwkv7-g1-2.9b-20250519-ctx4096.pth
+
+## 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. -->
+Install `flash-linear-attention` and the latest version of `transformers` before using this model:
+
+```bash
+pip install git+https://github.com/fla-org/flash-linear-attention
+pip install 'transformers>=4.48.0'
+```
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+You can use this model just as any other HuggingFace models:
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained('fla-hub/rwkv7-2.9B-g1', trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained('fla-hub/rwkv7-2.9B-g1', trust_remote_code=True) 
+model = model.cuda() # Supported on Nvidia/AMD/Intel eg. model.xpu()
+prompt = "What is a large language model?"
+messages = [
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+    enable_thinking=True  # Default is True, set to False to disable thinking
+)
+
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=1024,
+    do_sample=True,
+    temperature=1.0,
+    top_p=0.3,
+    repetition_penalty=1.2
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=False)[0]
+print(response)
+
+```
+
+
+## FAQ
+Q: safetensors metadata is none.
+
+A: upgrade transformers to >=4.48.0: `pip install 'transformers>=4.48.0'`
+
+
+<!--End Original Model Card-->
+
+---
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 If you find these models useful</span>
+
+Help me test my **AI-Powered Quantum Network Monitor Assistant** with **quantum-ready security checks**:  
+
+👉 [Quantum Network Monitor](https://readyforquantum.com/?assistant=open&utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme)  
+
+
+The full Open Source Code for the Quantum Network Monitor Service available at my github repos ( repos with NetworkMonitor in the name) : [Source Code Quantum Network Monitor](https://github.com/Mungert69). You will also find the code I use to quantize the models if you want to do it yourself [GGUFModelBuilder](https://github.com/Mungert69/GGUFModelBuilder)
+
+💬 **How to test**:  
+ Choose an **AI assistant type**:  
+   - `TurboLLM` (GPT-4.1-mini)  
+   - `HugLLM` (Hugginface Open-source models)  
+   - `TestLLM` (Experimental CPU-only)  
+
+### **What I’m Testing**  
+I’m pushing the limits of **small open-source models for AI network monitoring**, specifically:  
+- **Function calling** against live network services  
+- **How small can a model go** while still handling:  
+  - Automated **Nmap security scans**  
+  - **Quantum-readiness checks**  
+  - **Network Monitoring tasks**  
+
+🟡 **TestLLM** – Current experimental model (llama.cpp on 2 CPU threads on huggingface docker space):  
+- ✅ **Zero-configuration setup**  
+- ⏳ 30s load time (slow inference but **no API costs**) . No token limited as the cost is low.
+- 🔧 **Help wanted!** If you’re into **edge-device AI**, let’s collaborate!  
+
+### **Other Assistants**  
+🟢 **TurboLLM** – Uses **gpt-4.1-mini** :
+- **It performs very well but unfortunatly OpenAI charges per token. For this reason tokens usage is limited. 
+- **Create custom cmd processors to run .net code on Quantum Network Monitor Agents**
+- **Real-time network diagnostics and monitoring**
+- **Security Audits**
+- **Penetration testing** (Nmap/Metasploit)  
+
+🔵 **HugLLM** – Latest Open-source models:  
+- 🌐 Runs on Hugging Face Inference API. Performs pretty well using the lastest models hosted on Novita.
+
+### 💡 **Example commands you could test**:  
+1. `"Give me info on my websites SSL certificate"`  
+2. `"Check if my server is using quantum safe encyption for communication"`  
+3. `"Run a comprehensive security audit on my server"`
+4. '"Create a cmd processor to .. (what ever you want)" Note you need to install a [Quantum Network Monitor Agent](https://readyforquantum.com/Download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) to run the .net code on. This is a very flexible and powerful feature. Use with caution!
+
+### Final Word
+
+I fund the servers used to create these model files, run the Quantum Network Monitor service, and pay for inference from Novita and OpenAI—all out of my own pocket. All the code behind the model creation and the Quantum Network Monitor project is [open source](https://github.com/Mungert69). Feel free to use whatever you find helpful.
+
+If you appreciate the work, please consider [buying me a coffee](https://www.buymeacoffee.com/mahadeva) ☕. Your support helps cover service costs and allows me to raise token limits for everyone.
+
+I'm also open to job opportunities or sponsorship.
+
+Thank you! 😊

rwkv7-2.9B-g1-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd321a69b193a7e1a087e70b864e33b6b753feca5d0a03a4b57e45836cbcdca4
+size 5932472160

rwkv7-2.9B-g1-bf16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9a6c28dc151c1ec6897270438b2759b7058ac5e972794aaa59dd8f3bed95fa
+size 3573176160

rwkv7-2.9B-g1-f16_q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d117142f3388413a7e02260ad0cec31b443152e417b6905291361fdba3e747
+size 3573176160

rwkv7-2.9B-g1-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b024422a32f8724ab81e4c5f7cb1a3e5e26577624bd42f3475ee7a00d885de
+size 1540249760

rwkv7-2.9B-g1-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89aef706f00b9622e5caf7dcbbb721b6dd29910828399637fb12b9e8129f185
+size 1540249760

rwkv7-2.9B-g1-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e6aa0bb8a88efe9cebd5a58525512ad4b8e5ea400fa1d8d3c04b3e969415c4
+size 1540249760

rwkv7-2.9B-g1-iq3_xxs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86b07cb8e766ef107f16b5f46b921bd6eb2817558f6a5394dbfe2c72517c528
+size 1422284960

rwkv7-2.9B-g1-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f687c319bf3a0be95b881e6177c637265388b020a6d47c704f039f3687da3f6d
+size 1875794080

rwkv7-2.9B-g1-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd87b12c2d82ca0108f1ab30dc0100d23ae16b4eff1e078b02ba4e05952d0ef
+size 1791908000

rwkv7-2.9B-g1-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0db83fffd7fd94278fe421dd5f5ffc4530a943fa11fac8484fcded44c051d5
+size 1584814240

rwkv7-2.9B-g1-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd4421dc0850b97aa78e9183189ce788a76112dc7cd3ec15213d295acfac1ce
+size 1540249760

rwkv7-2.9B-g1-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f68038540e29bfc7283c49c24f7f7f669c991e2fd4fc31f4b8221b0b2451fd
+size 1832540320

rwkv7-2.9B-g1-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfceb509a2b52f5a4cb382ca18cd185361664f9f3f08d0561874efe2fedd2f43
+size 2010798240

rwkv7-2.9B-g1-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105e66b85ab4434097ebe2a91e321df62a85429c60719c619040484e0d879074
+size 1919047840

rwkv7-2.9B-g1-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931eb791aeb3f1e3d013d59058e58c8b8daf0d82aeaee7da95dd0b45dffb6c75
+size 1919047840

rwkv7-2.9B-g1-q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1e3f465db255c53a267555b1b6969d72327c45b4482a072b0edc069de1591c
+size 2189056160

rwkv7-2.9B-g1-q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fabc2d27295ab819f02fe14dce95e40e38c94e20863ebbf98ad10fbd1e3ed6fe
+size 2367314080

rwkv7-2.9B-g1-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f72cc02cf00fb0468e3a7edacb173baeebf85b6bb0684c1915a41ee3427c20e5
+size 2233620640

rwkv7-2.9B-g1-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fdee6bb185a2e6c0f9b06f0d66911279c0c063599214c2782354c2e22d69aa
+size 2233620640

rwkv7-2.9B-g1-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90309af01c48e3e3095098bff64e9969596b7581eee778b526c7bbb7b5a3f96
+size 2567854240

rwkv7-2.9B-g1-q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0968638d99f5a4e2e312555b03477b69d5431783b3523e42e5ddc826899a3b1
+size 3258603360

rwkv7-2.9B-g1.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce8dc79c3a0704e9151e0d08faacd4095a8f619d3fb9355298aeff36f8334ce
+size 4340350