---
license: other
pipeline_tag: text-generation
language:
- en
- zh
library_name: transformers
tags:
- mergekit
- qwen2
---

# FeatherQwen2-72B-v0.1

## Model Description
FeatherQwen is a 72B parameter language model created through a merge of Qwen2-72B-Instruct, calme2.1-72b, and magnum-72b-v1 using `model_stock`.

## Features
- 72 billion parameters
- Comes in 1,043 individual safetensor files
- Combines Magnum prose with Calam smarts

## Technical Specifications

### Architecture
- `Qwen2ForCasualLM`
- Models: Qwen2-72B-Instruct (base), calme2.1-72b, magnum-72b-v1
- Merged layers: 80
- Total tensors: 1,043

### Tensor Distribution
- Attention layers: 560 files
- MLP layers: 240 files
- Layer norms: 160 files
- Miscellaneous (embeddings, output): 83 files

### Merging
Custom script utilizing safetensors library.

## Usage

### Loading the Model
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained("leafspark/FeatherQwen2-72B-v0.1", 
                                             device_map="auto", 
                                             torch_dtype=torch.float16)
tokenizer = AutoTokenizer.from_pretrained("leafspark/FeatherQwen2-72B-v0.1")
```
### GGUFs

Find them here: [leafspark/FeatherQwen2-72B-v0.1-GGUF](https://huggingface.co/leafspark/FeatherQwen2-72B-v0.1-GGUF)


### Hardware Requirements
- Minimum ~140GB of storage
- ~140GB VRAM