docs: add model card

README.md

@@ -1,3 +1,55 @@
----
-license: unknown
----
+---
+license: unknown
+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
+- Models: Qwen2-72B-Instruct (base), calme2.1-72b, magnum-72b-v1
+- Merged layers: 79
+- Total tensors: 1,043
+
+### Tensor Distribution
+- Attention layers: 333 files
+- MLP layers: 333 files
+- Layer norms: 166 files
+- Miscellaneous (embeddings, output): 211 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")
+
+```
+
+### Hardware Requirements
+- Minimum ~140GB of storage
+- ~140GB VRAM