|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- mistral |
|
|
- 7b |
|
|
- lora |
|
|
- fine-tuning |
|
|
- indic-align |
|
|
- Malayalam |
|
|
- conversational-ai |
|
|
--- |
|
|
|
|
|
# Model Card for dhee-chat-mistral-ml |
|
|
|
|
|
A fine-tuned Malayalam conversational model based on `mistralai/Mistral-7B-v0.3` , optimized for Malayalam language understanding and generation. |
|
|
|
|
|
[](https://colab.research.google.com/drive/1kyyUEQ3LVwmTge8zN496Kx-SyPn7e8rV?usp=sharing) |
|
|
|
|
|
## Model Details |
|
|
|
|
|
* **Base Model:** Mistral 7B v0.3 |
|
|
* **Fine-tuning Method:** LoRA (Low-Rank Adaptation) |
|
|
* **Dataset:** `ai4bharat/indic-align` |
|
|
* **Language:** Malayalam |
|
|
* **Model ID:** `dheeyantra/dhee-chat-mistral-ml` |
|
|
|
|
|
## Intended Uses & Limitations |
|
|
|
|
|
This model is intended for use in Malayalam conversational applications, such as chatbots and virtual assistants. As it is fine-tuned on the `ai4bharat/indic-align` dataset, its knowledge and conversational style are primarily shaped by this data. |
|
|
|
|
|
Limitations: |
|
|
* The model's responses are based on the patterns and information present in the training data. It may generate incorrect or biased information. |
|
|
* Performance may vary depending on the complexity and nuance of the input. |
|
|
* The model is primarily focused on Malayalam and may not perform well in other languages or code-mixed scenarios unless explicitly trained for them. |
|
|
|
|
|
## How to Get Started with Hugging Face Transformers |
|
|
|
|
|
You can use the following Python code to load and run inference with the `dheeyantra/dhee-chat-mistral-ml` model: |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
import torch |
|
|
|
|
|
model_path = "dheeyantra/dhee-chat-mistral-ml" |
|
|
|
|
|
# Load tokenizer and model |
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path) |
|
|
model = AutoModelForCausalLM.from_pretrained(model_path) |
|
|
|
|
|
# Move model to GPU if available |
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu") |
|
|
model.to(device) |
|
|
|
|
|
# Prepare chat messages |
|
|
messages = [ |
|
|
{"role": "User", "content": "എത്ര വേദങ്ങളുണ്ട്?"}, |
|
|
{"role": "Dhee", "content": "നാല് വേദങ്ങളുണ്ട്: ഋഗ്വേദം, യജുർവേദം, സാമവേദം, അഥർവവേദം."}, |
|
|
{"role": "User", "content": "ഋഗ്വേദത്തെക്കുറിച്ച് കൂടുതൽ പറയൂ?"} |
|
|
] |
|
|
|
|
|
# Apply chat template to get prompt |
|
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
|
|
|
|
# Tokenize prompt |
|
|
inputs = tokenizer(prompt, return_tensors="pt").to(device) |
|
|
|
|
|
# Generate output |
|
|
with torch.no_grad(): |
|
|
output_ids = model.generate( |
|
|
**inputs, |
|
|
max_new_tokens=64, |
|
|
do_sample=True, |
|
|
temperature=0.9, |
|
|
top_p=0.95, |
|
|
pad_token_id=tokenizer.eos_token_id |
|
|
) |
|
|
|
|
|
# Decode generated text |
|
|
generated_text = tokenizer.decode(output_ids[0][inputs['input_ids'].shape[-1]:], skip_special_tokens=True) |
|
|
results = [{"generated_text": generated_text}] |
|
|
|
|
|
print("Generated text:") |
|
|
print(results[0]['generated_text']) |
|
|
``` |
|
|
|
|
|
## Disclaimer |
|
|
This model is provided as-is. Users should be aware of its potential limitations and biases before deploying it in any application. Responsible AI practices should be followed. |
|
|
|
|
|
|
|
|
## Training Configuration |
|
|
|
|
|
The model was fine-tuned using the following LoRA and training parameters: |
|
|
|
|
|
### LoRA Parameters: |
|
|
* `r`: 16 |
|
|
* `target_modules`: ["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj"] |
|
|
* `lora_alpha`: 16 |
|
|
* `lora_dropout`: 0 |
|
|
* `bias`: "none" |
|
|
* `use_gradient_checkpointing`: "unsloth" |
|
|
* `use_rslora`: False |
|
|
* `loftq_config`: None |
|
|
|
|
|
### Training Arguments: |
|
|
* `gradient_accumulation_steps`: 4 |
|
|
* `warmup_ratio`: 0.03 |
|
|
* `fp16`: True |
|
|
* `optim`: "adamw_8bit" |
|
|
* `max_seq_length`: 32768 |
|
|
|
|
|
## Acknowledgements |
|
|
We extend our sincere gratitude to the following organizations for their invaluable contributions to this project: |
|
|
|
|
|
* NxtGen: For generously providing the necessary infrastructure that powered the model training. |
|
|
* AI4Bharat: For developing and making available the indic-align dataset, which was crucial for fine-tuning this model. |
|
|
|
|
|
|
|
|
|
|
|
## Citation |
|
|
If you use this model in your research or applications, please cite: |
|
|
|
|
|
```bibtex |
|
|
@misc{dheenxtgen2025, |
|
|
title={ dhee-chat-mistral-ml : A Compact Language Model for Malayalam}, |
|
|
author={Dheeyantra Research Labs}, |
|
|
year={2025},} |
|
|
} |
|
|
``` |
