Upload README.md with huggingface_hub

README.md

@@ -1,27 +1,137 @@
-# DoloresAI-Merged (Fixed)
+---
+language:
+- en
+license: apache-2.0
+tags:
+- legal
+- immigration
+- assistant
+- qwen2
+- fine-tuned
+base_model: Qwen/Qwen2-7B-Instruct
+model_type: qwen2
+pipeline_tag: text-generation
+---
 
-This is a fixed version of the DoloresAI merged model with vocabulary mismatch resolved.
+# DoloresAI - Immigration Law Assistant
 
-## Changes
-- Fixed vocabulary size mismatch between model (151936) and tokenizer (151665)
-- Model embeddings resized to match tokenizer: 151665 tokens
-- Ready for deployment on HuggingFace Inference Endpoints
+DoloresAI is a specialized legal assistant fine-tuned on immigration law, designed to provide accurate and helpful information about U.S. immigration processes, visa types, and legal procedures.
 
 ## Model Details
-- Base Model: Qwen2-7B-Instruct
-- Fine-tuned for: Immigration law assistance
-- Fixed on: 2026-01-11 00:38:12
+
+- **Base Model**: Qwen/Qwen2-7B-Instruct
+- **Model Type**: Qwen2ForCausalLM
+- **Parameters**: 7B
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
+- **Vocabulary Size**: 151,665 tokens
+- **Precision**: FP16
+- **Context Length**: 32,768 tokens
+- **Fixed on**: 2026-01-11
+
+## Changes in This Version
+
+This is a fixed version of the DoloresAI merged model with vocabulary mismatch resolved:
+- Fixed vocabulary size mismatch between model (151,936) and tokenizer (151,665)
+- Model embeddings properly resized to match tokenizer: 151,665 tokens
+- Ready for deployment on HuggingFace Inference Endpoints without CUDA errors
+
+## Training
+
+This model was fine-tuned using LoRA adapters on immigration law data and then merged with the base model. The embeddings have been properly resized to match the tokenizer vocabulary size.
+
+## Intended Use
+
+DoloresAI is designed to assist with:
+- Immigration process information
+- Visa type explanations
+- Legal procedure guidance
+- Document requirements
+- Timeline estimates
+- Form instructions
+
+**Important**: This model provides information only and should not be considered legal advice. Always consult with a licensed immigration attorney for specific legal matters.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "JustiGuide/DoloresAI-Merged"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+prompt = "What are the requirements for an H-1B visa?"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.9,
+    do_sample=True
+)
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
 
 ## Deployment
-This model is ready to deploy on HuggingFace Inference Endpoints without CUDA errors.
 
-## Testing
+### HuggingFace Inference Endpoints
+
+For production deployment, use these environment variables to avoid CUDA errors:
+
+```bash
+PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
+CUDA_LAUNCH_BLOCKING=1
+TORCH_USE_CUDA_DSA=1
+TRANSFORMERS_OFFLINE=0
+HF_HUB_ENABLE_HF_TRANSFER=1
+MODEL_LOAD_TIMEOUT=600
+```
+
+Recommended hardware: Nvidia A10G or better
+
+## Verification
+
 The vocabulary sizes have been verified to match:
-- Model vocab size: 151665
-- Tokenizer vocab size: 151665
+- Model vocab size: 151,665 ✅
+- Tokenizer vocab size: 151,665 ✅
 - Match: ✅
 
-## Next Steps
-1. Upload to HuggingFace: `huggingface-cli upload JustiGuide/DoloresAI-Merged ./dolores-merged-fixed --repo-type model`
-2. Deploy new inference endpoint
-3. Update backend secrets with new endpoint URL
+## Limitations
+
+- Trained primarily on U.S. immigration law
+- Knowledge cutoff based on training data
+- Not a replacement for legal counsel
+- May require additional context for complex cases
+
+## License
+
+Apache 2.0
+
+## Citation
+
+```bibtex
+@misc{doloresai2025,
+  title={DoloresAI: Immigration Law Assistant},
+  author={JustiGuide},
+  year={2025},
+  publisher={HuggingFace},
+  howpublished={\url{https://huggingface.co/JustiGuide/DoloresAI-Merged}}
+}
+```
+
+## Model Card Authors
+
+JustiGuide Team
+
+## Model Card Contact
+
+For questions or issues, please open an issue on the model repository.