qwen-tamil-therapy-GGUF

Qwen 2.5-3B Tamil Therapy - GGUF Q4_K_M

Quantized GGUF version of Qwen 2.5-3B fine-tuned for empathetic therapy conversations in Tamil.

Model Details

• Base Model: Qwen/Qwen2.5-3B-Instruct
• Fine-tuned on: Tamil therapy conversations
• Quantization: Q4_K_M (4-bit)
• File Size: ~1.8 GB (from ~6 GB original)
• Format: GGUF (compatible with llama.cpp)
• Language: Tamil (தமிழ்)

Usage

With llama-cpp-python

from llama_cpp import Llama

llm = Llama(
    model_path="model.gguf",
    n_ctx=2048,
    n_threads=4,
    n_gpu_layers=35
)

output = llm(
    "User: எனக்கு மன அழுத்தம் உள்ளது\nTherapist:",
    max_tokens=200,
    temperature=0.7,
    top_p=0.9
)

print(output["choices"][0]["text"])

Intended Use

This model is designed for:

• Tamil-language mental health chatbots
• Therapy conversation simulation
• Empathetic response generation in Tamil
• Research in multilingual AI-assisted counseling

Limitations

• Not a replacement for professional therapy
• May produce incorrect or inappropriate responses
• Requires human oversight in production use
• Limited to Tamil language

License

Apache 2.0 (inherits from Qwen 2.5 base model)