Darmm/darmm-chat-kazakh-8b

darmm-chat-kazakh-8b

Conversational assistant for Kazakh (with Russian and English retained) — a QLoRA fine-tune of Qwen/Qwen3-8B on ~105k instruction pairs (65k Kazakh, 25k Russian, 15k English). Supersedes the darmm-text-generation line.

Benchmarks

Zero-shot multiple-choice accuracy via option log-prob scoring (non-thinking chat template). KazMMLU: 3,000-question sample (seed 42) over all Kazakh-language subjects; Belebele: full kaz_Cyrl test (900).

Reproducible with eval_chat.py in this repo.

Usage — generation settings matter

Use sampling, not greedy decoding: like the base model, long-form Kazakh degenerates into repetition under greedy decoding. Recommended settings:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Darmm/darmm-chat-kazakh-8b"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto")

messages = [{"role": "user", "content": "Наурыз мейрамы туралы айтып бер."}]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)
inputs = tok(text, return_tensors="pt").to(model.device)
out = model.generate(
    **inputs, max_new_tokens=512,
    do_sample=True, temperature=0.7, top_p=0.8, top_k=20, repetition_penalty=1.1,
)
print(tok.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

The model is trained for non-thinking mode (enable_thinking=False).

Training

• —QLoRA: 4-bit NF4 base, LoRA r=32 α=64 on all attention+MLP projections (59.9M trainable params)
• —Data: AmanMussa/kazakh-instruction-v2 (51k) + sabinaasker/kazakh_dolly (15k) + Russian (d0rj/alpaca-cleaned-ru, 25k) + English (yahma/alpaca-cleaned, 15k)
• —1 epoch, effective batch 32, lr 1e-4 cosine, max_seq 1024, bf16 compute, single A100

The LoRA adapter alone is at Darmm/darmm-chat-kazakh-8b-lora.

Limitations

• —Factual reliability is limited (38% KazMMLU): it can state dates, names, and facts confidently but wrongly — do not use as a factual reference without verification/RAG.
• —Much of the Kazakh training data is machine-translated; phrasing can be unnatural and occasionally awkward.
• —Greedy decoding degrades output — always use the sampling settings above.
• —Not safety-tuned beyond what the base model provides.

Built by Darmm · 2026-09 · Apache 2.0