Instructions to use IQuestLab/IQuest-Q1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IQuestLab/IQuest-Q1 with Transformers:

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

pipe = pipeline("text-generation", model="IQuestLab/IQuest-Q1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IQuestLab/IQuest-Q1", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IQuestLab/IQuest-Q1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IQuestLab/IQuest-Q1"
# 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-Q1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IQuestLab/IQuest-Q1

SGLang

How to use IQuestLab/IQuest-Q1 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-Q1" \
    --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-Q1",
		"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-Q1" \
        --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-Q1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IQuestLab/IQuest-Q1 with Docker Model Runner:
```
docker model run hf.co/IQuestLab/IQuest-Q1
```

IQuest-Q1 / config.json

yunyin007

Upload folder using huggingface_hub

313931e verified 13 days ago

Raw History Blame Contribute Delete

1.62 kB

	{
	"architectures": [
	"IQuestQ1ForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_out_scale": 1.0,
	"dense_intermediate_size": 12288,
	"dtype": "bfloat16",
	"embed_scale": 1.0,
	"enable_sink_attention": true,
	"eos_token_id": 0,
	"ffn_out_scale": 0.53881590608,
	"first_layer_attn_out_scale": 1.0,
	"first_layer_ffn_out_scale": 1.0,
	"first_layers_types": [
	"full_attention"
	],
	"fuse_sink_attention": true,
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"hybrid_layers_types_block": [
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"intermediate_size": 1536,
	"last_layers_types": [
	"full_attention",
	"full_attention",
	"full_attention"
	],
	"logit_scale": 1.0,
	"max_position_embeddings": 524288,
	"mlp_only_layers": [
	0
	],
	"model_type": "iquest_q1",
	"moe_router_dtype": "fp32",
	"enable_lm_head_fp32": true,
	"no_rope_layers": [],
	"num_attention_heads": 48,
	"num_experts": 256,
	"num_experts_per_tok": 8,
	"num_hidden_layers": 88,
	"num_hybrid_layers_block": 21,
	"num_key_value_heads": 8,
	"num_mtp_layers": 0,
	"rms_norm_eps": 1e-06,
	"rope_theta": 1000000,
	"rotary_dim": 32,
	"shared_kv_num_layers": 0,
	"shared_kv_source_begin": 0,
	"shared_kv_target_begin": 0,
	"sliding_window": 4096,
	"softmax_scale": null,
	"swa_rope_theta": 10000.0,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.1",
	"use_cache": true,
	"use_hybrid_layers": true,
	"use_over_encoding": false,
	"use_sliding_window": true,
	"vocab_size": 160000
	}