Instructions to use Darmm/darmm-chat-kazakh-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Darmm/darmm-chat-kazakh-8b with Transformers:

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

pipe = pipeline("text-generation", model="Darmm/darmm-chat-kazakh-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Darmm/darmm-chat-kazakh-8b")
model = AutoModelForCausalLM.from_pretrained("Darmm/darmm-chat-kazakh-8b", 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 Darmm/darmm-chat-kazakh-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Darmm/darmm-chat-kazakh-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Darmm/darmm-chat-kazakh-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Darmm/darmm-chat-kazakh-8b

SGLang

How to use Darmm/darmm-chat-kazakh-8b 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 "Darmm/darmm-chat-kazakh-8b" \
    --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": "Darmm/darmm-chat-kazakh-8b",
		"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 "Darmm/darmm-chat-kazakh-8b" \
        --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": "Darmm/darmm-chat-kazakh-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Darmm/darmm-chat-kazakh-8b with Docker Model Runner:
```
docker model run hf.co/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).

benchmark	Qwen3-8B (base)	this model
Belebele (kaz_Cyrl)	27.2%	39.8%
KazMMLU (kaz subjects)	27.9%	38.3%

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