Add pipeline_tag metadata and model documentation

README.md

@@ -0,0 +1,77 @@
+---
+language:
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- chess
+- neuron
+- aws-trainium
+- vllm
+- optimum-neuron
+base_model: karanps/ChessLM_Qwen3
+---
+
+# ChessLM Qwen3 - Neuron Traced for AWS Trainium/Inferentia
+
+This is a Neuron-traced version of [karanps/ChessLM_Qwen3](https://huggingface.co/karanps/ChessLM_Qwen3) optimized for AWS Trainium (trn1) and Inferentia (inf2) instances using vLLM.
+
+## Model Details
+
+- **Base Model**: Qwen3-2B fine-tuned for chess
+- **Compilation**: optimum-neuron[vllm]==0.3.0
+- **Target Hardware**: AWS Trainium (trn1) / Inferentia (inf2)
+- **Precision**: BF16
+- **Tensor Parallelism**: 2 cores
+- **Batch Size**: 1
+- **Max Sequence Length**: 2048
+
+## Requirements
+
+```bash
+pip install optimum-neuron[vllm]==0.3.0
+pip install neuronx-distributed --extra-index-url=https://pip.repos.neuron.amazonaws.com
+```
+
+## Usage
+
+### Loading the Model
+
+```python
+from optimum.neuron import NeuronModelForCausalLM
+from transformers import AutoTokenizer
+
+# Load the traced model
+model = NeuronModelForCausalLM.from_pretrained("kunhunjon/ChessLM_Qwen3_Trainium")
+tokenizer = AutoTokenizer.from_pretrained("kunhunjon/ChessLM_Qwen3_Trainium")
+
+# Run inference
+prompt = "e2e4"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=20)
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)
+```
+
+### Hardware Requirements
+
+- AWS Trainium (trn1.32xlarge, trn1.2xlarge) or Inferentia (inf2) instances
+- At least 2 Neuron cores (as configured during tracing)
+- Minimum 32GB RAM recommended
+
+## Compilation Details
+
+This model was traced with the following parameters:
+- `batch_size=1`
+- `sequence_length=2048`
+- `num_cores=2`
+- `auto_cast_type="bf16"`
+- vLLM-compatible compilation
+
+## License
+
+This model inherits the license from the base model [karanps/ChessLM_Qwen3](https://huggingface.co/karanps/ChessLM_Qwen3).
+
+## Citation
+
+If you use this model, please cite the original ChessLM model and AWS Neuron tools.