Instructions to use IQuestLab/IQuest-Coder-V1-40B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IQuestLab/IQuest-Coder-V1-40B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="IQuestLab/IQuest-Coder-V1-40B-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IQuestLab/IQuest-Coder-V1-40B-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IQuestLab/IQuest-Coder-V1-40B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IQuestLab/IQuest-Coder-V1-40B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IQuestLab/IQuest-Coder-V1-40B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IQuestLab/IQuest-Coder-V1-40B-Instruct

SGLang

How to use IQuestLab/IQuest-Coder-V1-40B-Instruct 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 "IQuestLab/IQuest-Coder-V1-40B-Instruct" \
    --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": "IQuestLab/IQuest-Coder-V1-40B-Instruct",
		"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 "IQuestLab/IQuest-Coder-V1-40B-Instruct" \
        --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": "IQuestLab/IQuest-Coder-V1-40B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IQuestLab/IQuest-Coder-V1-40B-Instruct with Docker Model Runner:
```
docker model run hf.co/IQuestLab/IQuest-Coder-V1-40B-Instruct
```

IQuestLab is more like IFakeEvals...

by coolpoodle - opened Jan 3

Discussion

coolpoodle

Jan 3

but the loop attention is cool, so I open sourced it

https://huggingface.co/coolpoodle/Qwen3-0.6B-Looped

gg2ez

DamienRodgers274

Jan 3

holy smokes

aaron-newsome

Jan 6

i'm learning to resist the urge to waste any time at all on models, solely based on benchmark scores. theres a bunch of models that claim to beat the best models from major providers, but really they're just a waste of time when you try to do real work. if these companies put as much energy into making models that do real work instead of benchmark maxing, that would amazing for the local model camp. shoutout to MiniMax-M2.1 though, that one does do a pretty good job.

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