The general-purpose instruction/chat model of the
Dharmamitra Qwen3.5 family: a multi-turn SFT of
mitra-qwen35-base-stage2
for Buddhist-studies conversation — closed-book Buddhism Q&A plus
translation and translation-refinement assistance for classical languages
(Sanskrit, Tibetan, Buddhist Chinese, Pāli).
This is the recommended entry point if you want to
talk to the mitra
family; use the stage-2 base for raw translation pipelines and the
embedder for
retrieval.
1import torch
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4tok = AutoTokenizer.from_pretrained("buddhist-nlp/mitra-qwen35-it")
5model = AutoModelForCausalLM.from_pretrained(
6 "buddhist-nlp/mitra-qwen35-it", dtype=torch.bfloat16, device_map="cuda"
7)
8messages = [{"role": "user", "content":
9 "What is the difference between śamatha and vipaśyanā?"}]
10inputs = tok.apply_chat_template(messages, add_generation_prompt=True,
11 return_dict=True, return_tensors="pt").to(model.device)
12out = model.generate(**inputs, max_new_tokens=512)
13print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Tibetan may be given in Wylie transliteration; Sanskrit and Pāli in IAST.
If you use this model, please cite the Dharmamitra project
(
https://dharmamitra.org). A technical report is in preparation.
