Instructions to use buddhist-nlp/gemma-2-mitra-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use buddhist-nlp/gemma-2-mitra-chat with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="buddhist-nlp/gemma-2-mitra-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("buddhist-nlp/gemma-2-mitra-chat")
model = AutoModelForCausalLM.from_pretrained("buddhist-nlp/gemma-2-mitra-chat", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use buddhist-nlp/gemma-2-mitra-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "buddhist-nlp/gemma-2-mitra-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "buddhist-nlp/gemma-2-mitra-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/buddhist-nlp/gemma-2-mitra-chat

SGLang

How to use buddhist-nlp/gemma-2-mitra-chat with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "buddhist-nlp/gemma-2-mitra-chat" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "buddhist-nlp/gemma-2-mitra-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "buddhist-nlp/gemma-2-mitra-chat" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "buddhist-nlp/gemma-2-mitra-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use buddhist-nlp/gemma-2-mitra-chat with Docker Model Runner:
```
docker model run hf.co/buddhist-nlp/gemma-2-mitra-chat
```

gemma-2-mitra-chat

A multi-turn chat model for Buddhist studies from the Dharmamitra project: closed-book Buddhism Q&A plus a translation/refinement assistant for classical languages (Sanskrit, Tibetan, Buddhist Chinese, Pāli), speaking the standard gemma-2 chat protocol — it works out of the box with Ollama / llama.cpp multi-turn templates.

Built by full-parameter SFT of buddhist-nlp/gemma2-mitra-base (9.5B, Buddhist-domain continued pretraining) on ~10k examples: ~5k closed-book Buddhism Q&A (mined open-book, references removed so the knowledge is distilled into the weights) and ~5k translation/refine tasks (zh/sa/bo/pi, half with retrieved reference passages). Completion-only loss over full chat histories; EOS is <end_of_turn>, so turns close correctly in stock chat runtimes.

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("buddhist-nlp/gemma-2-mitra-chat")
model = AutoModelForCausalLM.from_pretrained(
    "buddhist-nlp/gemma-2-mitra-chat", dtype=torch.bfloat16, device_map="cuda"
)

messages = [{"role": "user", "content":
    "Translate into English: 'di skad bdag gis thos pa dus gcig na"}]
inputs = tok.apply_chat_template(messages, add_generation_prompt=True,
                                 return_dict=True, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=256)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Tibetan may be given in Wylie transliteration (as in the mitra convention); Sanskrit and Pāli in IAST.

Training details

Base: buddhist-nlp/gemma2-mitra-base
Full-parameter SFT (TRL, completion-only loss, gemma-2 chat template), LR 1e-5, effective batch 64, cosine schedule, bf16; best checkpoint at step 220
Data: combined closed-book Q&A + translation/refinement corpus (~10k multi-turn examples)

Related models

Part of the buddhist-nlp gemma-2 Mitra family; see also the newer Qwen3.5-based generation: buddhist-nlp/mitra-qwen35-base, buddhist-nlp/mitra-qwen35-embedder.

Citation

If you use this model, please cite the Dharmamitra project (https://dharmamitra.org).

Downloads last month: 15

Safetensors

Model size

9B params

Tensor type

BF16

Model tree for buddhist-nlp/gemma-2-mitra-chat

Base model

buddhist-nlp/gemma2-mitra-base

Finetuned

(2)

this model

Collection including buddhist-nlp/gemma-2-mitra-chat

Gemma-2 Mitra (2024)

Collection

The first-generation Dharmamitra model family (trained August 2024) on gemma-2: base, instruct, embedder — plus the 2026 chat SFT. • 7 items • Updated 1 day ago