Instructions to use bknyaz/Qwen3-Coder-Next-REAM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bknyaz/Qwen3-Coder-Next-REAM with Transformers:

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

pipe = pipeline("text-generation", model="bknyaz/Qwen3-Coder-Next-REAM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("bknyaz/Qwen3-Coder-Next-REAM")
model = AutoModelForCausalLM.from_pretrained("bknyaz/Qwen3-Coder-Next-REAM")
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

vLLM

How to use bknyaz/Qwen3-Coder-Next-REAM with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/bknyaz/Qwen3-Coder-Next-REAM

SGLang

How to use bknyaz/Qwen3-Coder-Next-REAM 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 "bknyaz/Qwen3-Coder-Next-REAM" \
    --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": "bknyaz/Qwen3-Coder-Next-REAM",
		"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 "bknyaz/Qwen3-Coder-Next-REAM" \
        --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": "bknyaz/Qwen3-Coder-Next-REAM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use bknyaz/Qwen3-Coder-Next-REAM with Docker Model Runner:
```
docker model run hf.co/bknyaz/Qwen3-Coder-Next-REAM
```

make REAM models for exactly one-two programming languages

by zotona0 - opened Feb 17

Discussion

zotona0

Feb 17

i see, what for callibration was used https://huggingface.co/datasets/bigcode/the-stack-smol
we can filter dataset by lang field.
is it possible with preserve near original perfomance?

bknyaz

Owner Feb 18

we used a random subset without any filtering, and not planning to try filtering at this moment, but hopefully will release the code soon, so it could be done by others

bknyaz changed discussion status to closed Feb 18

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment