AyurParam: A State-of-the-Art Bilingual Language Model for Ayurveda
Paper • 2511.02374 • Published • 5
How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf A-Aryam/AyurParam-GGUF:Q4_K_M# Run inference directly in the terminal:
llama cli -hf A-Aryam/AyurParam-GGUF:Q4_K_MUse pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf A-Aryam/AyurParam-GGUF:Q4_K_M# Run inference directly in the terminal:
./llama-cli -hf A-Aryam/AyurParam-GGUF:Q4_K_MBuild from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf A-Aryam/AyurParam-GGUF:Q4_K_M# Run inference directly in the terminal:
./build/bin/llama-cli -hf A-Aryam/AyurParam-GGUF:Q4_K_MUse Docker
docker model run hf.co/A-Aryam/AyurParam-GGUF:Q4_K_MQuick Links
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
- Open LM Studio
- Go to Search tab → search
A-Aryam/AyurParam-GGUF - Download
AyurParam-Q4_K_M.gguf - 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
- Downloads last month
- 54
Hardware compatibility
Log In to add your hardware
4-bit
16-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for A-Aryam/AyurParam-GGUF
Base model
bharatgenai/Param-1 Finetuned
bharatgenai/Param-1-2.9B-Instruct Finetuned
bharatgenai/AyurParam
Install (macOS, Linux)
# Start a local OpenAI-compatible server with a web UI: llama serve -hf A-Aryam/AyurParam-GGUF:Q4_K_M# Run inference directly in the terminal: llama cli -hf A-Aryam/AyurParam-GGUF:Q4_K_M