A-Aryam/AyurParam-GGUF

AyurParam GGUF

GGUF conversions of bharatgenai/AyurParam for local inference via Ollama and llama.cpp.

Converted by Aarya R. Thakar for use in ReassureAI — a hybrid AI healthcare assistant integrating modern biomedical and Ayurvedic guidance.

---

Available Variants

File	Quantization	Size	Quality	Recommended For
AyurParam-F16.gguf	F16	~5.34GB	Full precision	Evaluation, testing
AyurParam-Q4_K_M.gguf	Q4_K_M	~1.7GB	Good	✅ Production use

---

Usage

With Ollama

# Pull directly from HuggingFace
ollama run hf.co/A-Aryam/AyurParam-GGUF:Q4_K_M

# Or download and create manually
ollama create ayurparam -f Modelfile

Modelfile:

FROM ./AyurParam-Q4_K_M.gguf
PARAMETER temperature 0.6
PARAMETER top_p 0.95
PARAMETER top_k 50

With llama.cpp

./llama-cli -m AyurParam-Q4_K_M.gguf \
  -p "<user> What is Vata dosha? <assistant>" \
  --temp 0.6 --top-p 0.95

With LM Studio

1. Open LM Studio
2. Go to Search tab → search A-Aryam/AyurParam-GGUF
3. Download AyurParam-Q4_K_M.gguf
4. Load the model and start chatting

---

Prompt Format

<user> your question here <assistant>

Example:

<user> What is the Ayurvedic treatment for Amavata? <assistant>

---

Conversion Details

• Converted: March 2025
• Tool: llama.cpp (standard conversion pipeline)
• Source: bharatgenai/AyurParam
• Original license: CC-BY-4.0

---

Original Model

• Model: bharatgenai/AyurParam
• Organization: BharatGen AI
• Base: Param-1-2.9B-Instruct → fine-tuned on Ayurvedic dataset
• Paper: Coming soon (arxiv:2511.02374)

---

License

CC-BY-4.0 — same as the original model. Attribution: BharatGen AI / bharatgenai/AyurParam