Instructions to use issai/Qwen3.5-9B-Base-Kazakh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use issai/Qwen3.5-9B-Base-Kazakh with Transformers:

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

pipe = pipeline("text-generation", model="issai/Qwen3.5-9B-Base-Kazakh")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("issai/Qwen3.5-9B-Base-Kazakh")
model = AutoModelForCausalLM.from_pretrained("issai/Qwen3.5-9B-Base-Kazakh", 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 issai/Qwen3.5-9B-Base-Kazakh with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "issai/Qwen3.5-9B-Base-Kazakh"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "issai/Qwen3.5-9B-Base-Kazakh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/issai/Qwen3.5-9B-Base-Kazakh

SGLang

How to use issai/Qwen3.5-9B-Base-Kazakh 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 "issai/Qwen3.5-9B-Base-Kazakh" \
    --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": "issai/Qwen3.5-9B-Base-Kazakh",
		"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 "issai/Qwen3.5-9B-Base-Kazakh" \
        --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": "issai/Qwen3.5-9B-Base-Kazakh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use issai/Qwen3.5-9B-Base-Kazakh with Docker Model Runner:
```
docker model run hf.co/issai/Qwen3.5-9B-Base-Kazakh
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3.5-9B-Base-Kazakh

Kazakh-adapted continued-pretraining (CPT) of Qwen/Qwen3.5-9B-Base.

It extends the original Qwen3.5 base with 16K new Kazakh tokens and continues pretraining on a large Kazakh + English corpus, to improve Kazakh fluency and knowledge while retaining the original English capabilities.

Training details

Tokenizer extension (+16K). The Qwen3.5 tokenizer (248,320) was extended with 16,000 new, predominantly Cyrillic-Kazakh tokens → 264,192 total. New embedding rows were initialized with FVT (Fast Vocabulary Transfer): each new row is the unweighted mean of its constituent original sub-token embeddings, giving the model a warm start on the new vocabulary. Applied under untied embeddings (FVT applied to both the input embeddings and the separate lm_head).
Continued pretraining. Full-parameter CPT for one epoch at sequence length 32,768, learning rate 1e-5 (cosine → 1e-6, 2% warmup), weight decay 0.1, gradient clip 1.0, on 2× 8×H100.

Data

~15.9B new tokenizer tokens total with a 50/50 Kazakh:English mix. The Kazakh half is a cross-source deduplicated corpus (FineWeb-2, CulturaX, FinePDFs, FineWiki). The English half is a replay mix for retention (FineWeb-Edu web, Nemotron-CC math + wiki-rewrite, Stack-Edu code). Additional curated Kazakh sets (cultural/QA/encyclopedic) were folded in and upsampled 3×.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

name = "issai/Qwen3.5-9B-Base-Kazakh"
tokenizer = AutoTokenizer.from_pretrained(name)
model = AutoModelForCausalLM.from_pretrained(name, torch_dtype="bfloat16", device_map="auto")

prompt = "Сұрақ: Үстірт қорығы қай облыста орналасқан?\nЖауап:"

ids = tokenizer(prompt, return_tensors="pt").to(model.device)

print(tokenizer.decode(model.generate(**ids, max_new_tokens=100)[0][ids.input_ids.shape[1]:]))