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

Libraries

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

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

pipe = pipeline("text-generation", model="IQuestLab/IQuest-Coder-V1-40B-Loop-Thinking", 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-Loop-Thinking", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Use Docker

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

SGLang

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

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

IQuest-Coder-V1-40B-Loop-Thinking

File size: 1,039 Bytes

{
    "_name_or_path": "iquestloopcoder",
    "architectures": [
      "IQuestLoopCoderForCausalLM"
    ],
    "model_type": "iquestloopcoder",
    "vocab_size": 76800,
    "hidden_size": 5120,
    "intermediate_size": 27648,
    "num_hidden_layers": 80,
    "eos_token_id": [2, 75864, 75869],
    "num_attention_heads": 40,
    "num_key_value_heads": 8,
    "head_dim": 128,
    "hidden_act": "silu",
    "max_position_embeddings": 131072,
    "initializer_range": 0.02,
    "rms_norm_eps": 1e-05,
    "use_cache": true,
    "tie_word_embeddings": false,
    "rope_theta": 500000,
    "attention_bias": false,
    "attention_dropout": 0.0,
    "mlp_bias": false,
    "loop_num": 2,
    "loop_window_size": 8192,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.55.4",
    "auto_map": {
      "AutoConfig": "configuration_iquestloopcoder.IQuestLoopCoderConfig",
      "AutoModel": "modeling_iquestloopcoder.IQuestLoopCoderModel",
      "AutoModelForCausalLM": "modeling_iquestloopcoder.IQuestLoopCoderForCausalLM"
    }
  }