Instructions to use buddhist-nlp/mitra-qwen35-base-stage1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use buddhist-nlp/mitra-qwen35-base-stage1 with Transformers:

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

pipe = pipeline("text-generation", model="buddhist-nlp/mitra-qwen35-base-stage1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("buddhist-nlp/mitra-qwen35-base-stage1")
model = AutoModelForCausalLM.from_pretrained("buddhist-nlp/mitra-qwen35-base-stage1", 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/mitra-qwen35-base-stage1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "buddhist-nlp/mitra-qwen35-base-stage1"
# 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/mitra-qwen35-base-stage1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/buddhist-nlp/mitra-qwen35-base-stage1

SGLang

How to use buddhist-nlp/mitra-qwen35-base-stage1 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/mitra-qwen35-base-stage1" \
    --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/mitra-qwen35-base-stage1",
		"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/mitra-qwen35-base-stage1" \
        --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/mitra-qwen35-base-stage1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use buddhist-nlp/mitra-qwen35-base-stage1 with Docker Model Runner:
```
docker model run hf.co/buddhist-nlp/mitra-qwen35-base-stage1
```

mitra-qwen35-base-stage1

The stage-1 continued-pretraining checkpoint of the Dharmamitra model family: Qwen3.5-9B-Base after ~30B tokens of continued pretraining on classical Buddhist corpora (28,500 steps × ~1.05M tokens, 8k context; training loss 1.85 → 1.16).

This is a base (non-instruction) model, released as a research artifact and as the recommended starting point for your own SFT on Buddhist-domain tasks. For an instruction-following model from this lineage use buddhist-nlp/mitra-qwen35-base-stage2 (this checkpoint + stage-2 SFT); for retrieval use buddhist-nlp/mitra-qwen35-embedder.

Corpus and script conventions

The pretraining corpus covers Sanskrit, Tibetan, Buddhist Chinese, and Pāli source texts with related secondary literature.

Tibetan is native Tibetan script (Unicode) — unlike some downstream finetunes in this family, stage 1 was not trained on Wylie transliteration.
Sanskrit and Pāli are predominantly IAST romanization; Chinese is Chinese script.

Usage

Plain causal-LM completion (no chat template — this is a base model):

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("buddhist-nlp/mitra-qwen35-base-stage1")
model = AutoModelForCausalLM.from_pretrained(
    "buddhist-nlp/mitra-qwen35-base-stage1", dtype=torch.bfloat16, device_map="cuda"
)

prompt = "evaṃ mayā śrutam ekasmin samaye bhagavān"
inputs = tok(prompt, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=64, do_sample=False)
print(tok.decode(out[0], skip_special_tokens=True))

Model details

Base: Qwen/Qwen3.5-9B-Base
Continued pretraining: 28,500 optimizer steps at ~~1.05M tokens/update (~~29.9B tokens), 8,192-token packed sequences, bf16, ZeRO-2
This checkpoint is the deliberate end of stage 1 (training was moved to stage-2 SFT from here)

Citation

If you use this model, please cite the Dharmamitra project (https://dharmamitra.org). A technical report is in preparation.

Downloads last month: 32

Safetensors

Model size

9B params

Tensor type

BF16

Collection including buddhist-nlp/mitra-qwen35-base-stage1

Mitra Qwen3.5 (2026)

Collection

Dharmamitra's Qwen3.5-9B family for classical Buddhist literature: CPT base, instruction SFT, and retrieval embedder. Trained in July 2026. • 6 items • Updated 14 days ago