Instructions to use mahernaija/Qwen3.5-27B-Coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mahernaija/Qwen3.5-27B-Coder with Transformers:

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

pipe = pipeline("text-generation", model="mahernaija/Qwen3.5-27B-Coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("mahernaija/Qwen3.5-27B-Coder")
model = AutoModelForMultimodalLM.from_pretrained("mahernaija/Qwen3.5-27B-Coder")
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 mahernaija/Qwen3.5-27B-Coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mahernaija/Qwen3.5-27B-Coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mahernaija/Qwen3.5-27B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mahernaija/Qwen3.5-27B-Coder

SGLang

How to use mahernaija/Qwen3.5-27B-Coder 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 "mahernaija/Qwen3.5-27B-Coder" \
    --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": "mahernaija/Qwen3.5-27B-Coder",
		"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 "mahernaija/Qwen3.5-27B-Coder" \
        --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": "mahernaija/Qwen3.5-27B-Coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mahernaija/Qwen3.5-27B-Coder with Docker Model Runner:
```
docker model run hf.co/mahernaija/Qwen3.5-27B-Coder
```

Qwen3.5-27B-Coder / README.md

mahernaija

Upload Qwen3.5-27B-Coder: LoRA fine-tuned for coding

5426137 verified 2 months ago

preview code

raw

history blame contribute delete

3.04 kB

metadata

license: apache-2.0
base_model: Qwen/Qwen3.5-27B
tags:
  - code
  - lora
  - fine-tuned
  - qwen3.5
  - coding
  - python
  - javascript
  - rust
datasets:
  - ise-uiuc/Magicoder-Evol-Instruct-110K
  - sahil2801/CodeAlpaca-20k
  - Vezora/Tested-143k-Python-Alpaca
  - iamtarun/python_code_instructions_18k_alpaca
language:
  - en
pipeline_tag: text-generation
library_name: transformers

Qwen3.5-27B-Coder

Fine-tuned version of Qwen/Qwen3.5-27B specialized for coding tasks.

Training Details

Parameter	Value
Base model	Qwen/Qwen3.5-27B (27B dense, Apache 2.0)
Method	LoRA r=64, alpha=128, all-linear projections
Precision	BF16
Framework	HuggingFace SFTTrainer + PEFT + DeepSpeed ZeRO-2
Hardware	16× NVIDIA H200 SXM (141 GB each), 2 nodes
GPU utilization	91% VRAM, 91-100% compute
Training steps	250 (early stopped — loss plateaued)
Training time	~4 hours
Final loss	0.70 (down from 1.13, -40%)
Final accuracy	80.0% token accuracy

Datasets

Dataset	Examples	Purpose
Magicoder-Evol-Instruct-110K	110K	Complex coding tasks from real GitHub code
CodeAlpaca-20K	20K	Short tasks, broad language coverage
Tested-143k-Python-Alpaca	143K	Execution-verified Python code
python_code_instructions_18k	18K	Python idioms and patterns
Total	291K

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "mahernaija/Qwen3.5-27B-Coder",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("mahernaija/Qwen3.5-27B-Coder")

messages = [{"role": "user", "content": "Write a Python binary search function with type hints."}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Evaluation

Fine-tuned model compared to base on 10 coding prompts:

7/10 prompts: Fine-tuned model produces faster, more concise responses
Refactoring: 70% faster response
Testing: 59% faster response
Loss improvement: 40% reduction over base model

Training Infrastructure

Trained on Nebius.ai cloud using Soperator (Kubernetes-managed Slurm):

2 nodes × 8 NVIDIA H200 SXM GPUs
InfiniBand 400 Gb/s inter-node communication
DeepSpeed ZeRO-2 for optimizer/gradient sharding
Gradient checkpointing with use_reentrant=False

Limitations

Primarily optimized for Python (70% of training data)
Other languages (JS, Rust, Go) improved but less than Python
Not trained on repo-level tasks (SWE-bench style)
Best for function/class level code generation and bug fixing

License

Apache 2.0 (same as base model)