Instructions to use Akahsizrr/Qwen3.8-27B-Code-Tools-Merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Akahsizrr/Qwen3.8-27B-Code-Tools-Merged with Transformers:

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

pipe = pipeline("text-generation", model="Akahsizrr/Qwen3.8-27B-Code-Tools-Merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Akahsizrr/Qwen3.8-27B-Code-Tools-Merged")
model = AutoModelForCausalLM.from_pretrained("Akahsizrr/Qwen3.8-27B-Code-Tools-Merged", 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 Akahsizrr/Qwen3.8-27B-Code-Tools-Merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Akahsizrr/Qwen3.8-27B-Code-Tools-Merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Akahsizrr/Qwen3.8-27B-Code-Tools-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Akahsizrr/Qwen3.8-27B-Code-Tools-Merged

SGLang

How to use Akahsizrr/Qwen3.8-27B-Code-Tools-Merged 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 "Akahsizrr/Qwen3.8-27B-Code-Tools-Merged" \
    --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": "Akahsizrr/Qwen3.8-27B-Code-Tools-Merged",
		"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 "Akahsizrr/Qwen3.8-27B-Code-Tools-Merged" \
        --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": "Akahsizrr/Qwen3.8-27B-Code-Tools-Merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Akahsizrr/Qwen3.8-27B-Code-Tools-Merged with Docker Model Runner:
```
docker model run hf.co/Akahsizrr/Qwen3.8-27B-Code-Tools-Merged
```

Qwen3.8-27B Code-Tools-Merged

Full merged checkpoint of the Qwen3.8-27B coding/reasoning/tool-calling fine-tune stack.

Stack (merged in order)

Qwen/Qwen3.8-27B (base)
Akahsizrr/qwen3.8-27b-lora-xhigh-code-tools-1k (LoRA, merged)
Akahsizrr/qwen3.8-27b-lora-kimi-k3-tools-code-instr (LoRA, merged)
Akahsizrr/qwen3.8-27b-lora-comp-v1 (LoRA, merged)

Benchmark

LiveCodeBench v6 (test6.jsonl, 175 problems, pass@1, n=1, temp 0.2, top_p 0.95, max_tokens 32768, xhigh reasoning effort, vLLM 0.28.0):

3-adapter stack: 76.0% (133/175) with adapters 1+2 only; 75.4% (132/175) with comp-v1 included.

Usage (vLLM)

from vllm import LLM, SamplingParams
llm = LLM(model="Akahsizrr/Qwen3.8-27B-Code-Tools-Merged", dtype="bfloat16",
          max_model_len=36864, gpu_memory_utilization=0.90, enable_prefix_caching=True)
sp = SamplingParams(n=1, max_tokens=32768, temperature=0.2, top_p=0.95)
out = llm.chat(messages, sp, chat_template_kwargs={"reasoning_effort": "xhigh"})

Reasoning is emitted between / ; extract the final code block from the answer.

Downloads last month: 211

Safetensors

Model size

27B params

Tensor type

BF16

Model tree for Akahsizrr/Qwen3.8-27B-Code-Tools-Merged

Base model

Qwen/Qwen3.8-27B

Finetuned

(316)

this model