Instructions to use nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("cerebras/Qwen3-Coder-REAP-25B-A3B")
model = PeftModel.from_pretrained(base_model, "nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA")

Transformers

How to use nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA with Transformers:

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

pipe = pipeline("text-generation", model="nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA

SGLang

How to use nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA 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 "nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA" \
    --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": "nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA",
		"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 "nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA" \
        --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": "nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA with Docker Model Runner:
```
docker model run hf.co/nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA
```

Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA

Standalone adapter used in Hemlock-Qwen3-Coder-REAP-25B-A3B

Downloads last month: 10

Model tree for nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA

Base model

Qwen/Qwen3-Coder-30B-A3B-Instruct

Finetuned

cerebras/Qwen3-Coder-REAP-25B-A3B

Adapter

(1)

this model

nbeerbower
/

Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA

Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA

Model tree for nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA

Dataset used to train nbeerbower/Hemlock-Qwen3-Coder-REAP-25B-A3B-LORA