Instructions to use IAAR-Shanghai/Metis-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IAAR-Shanghai/Metis-9B with Transformers:

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

pipe = pipeline("text-generation", model="IAAR-Shanghai/Metis-9B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IAAR-Shanghai/Metis-9B", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IAAR-Shanghai/Metis-9B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IAAR-Shanghai/Metis-9B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IAAR-Shanghai/Metis-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IAAR-Shanghai/Metis-9B

SGLang

How to use IAAR-Shanghai/Metis-9B 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 "IAAR-Shanghai/Metis-9B" \
    --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": "IAAR-Shanghai/Metis-9B",
		"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 "IAAR-Shanghai/Metis-9B" \
        --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": "IAAR-Shanghai/Metis-9B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IAAR-Shanghai/Metis-9B with Docker Model Runner:
```
docker model run hf.co/IAAR-Shanghai/Metis-9B
```

Metis-9B / config.json

astarkkk

Add files using upload-large-folder tool

e903a9a verified 14 days ago

Raw

History Blame Contribute Delete

5.43 kB

	{
	"architectures": [
	"MetisForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_metis.MetisConfig",
	"AutoModelForCausalLM": "modeling_metis.MetisForCausalLM"
	},
	"backbone_configs": {
	"_name_or_path": "/mnt/afs/models/Qwen3.5-9B",
	"architectures": [
	"Qwen3_5ForConditionalGeneration"
	],
	"chunk_size_feed_forward": 0,
	"dtype": null,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"image_token_id": 248056,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"model_type": "qwen3_5",
	"output_attentions": false,
	"output_hidden_states": false,
	"problem_type": null,
	"return_dict": true,
	"text_config": {
	"_name_or_path": "",
	"architectures": null,
	"attention_bias": false,
	"attention_dropout": 0.0,
	"attn_output_gate": true,
	"bos_token_id": null,
	"chunk_size_feed_forward": 0,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"full_attention_interval": 4,
	"head_dim": 256,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"initializer_range": 0.02,
	"intermediate_size": 12288,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"layer_types": [
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention",
	"linear_attention",
	"linear_attention",
	"linear_attention",
	"full_attention"
	],
	"linear_conv_kernel_dim": 4,
	"linear_key_head_dim": 128,
	"linear_num_key_heads": 16,
	"linear_num_value_heads": 32,
	"linear_value_head_dim": 128,
	"mamba_ssm_dtype": "float32",
	"max_position_embeddings": 262144,
	"mlp_only_layers": [],
	"model_type": "qwen3_5_text",
	"mtp_num_hidden_layers": 1,
	"mtp_use_dedicated_embeddings": false,
	"num_attention_heads": 16,
	"num_hidden_layers": 32,
	"num_key_value_heads": 4,
	"output_attentions": false,
	"output_hidden_states": false,
	"pad_token_id": null,
	"partial_rotary_factor": 0.25,
	"problem_type": null,
	"return_dict": true,
	"rms_norm_eps": 1e-06,
	"rope_parameters": {
	"mrope_interleaved": true,
	"mrope_section": [
	11,
	11,
	10
	],
	"partial_rotary_factor": 0.25,
	"rope_theta": 10000000,
	"rope_type": "default"
	},
	"tie_word_embeddings": false,
	"use_cache": true,
	"vocab_size": 248320
	},
	"tie_word_embeddings": false,
	"video_token_id": 248057,
	"vision_config": {
	"_name_or_path": "",
	"architectures": null,
	"chunk_size_feed_forward": 0,
	"deepstack_visual_indexes": [],
	"depth": 27,
	"dtype": null,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 1152,
	"id2label": {
	"0": "LABEL_0",
	"1": "LABEL_1"
	},
	"in_channels": 3,
	"initializer_range": 0.02,
	"intermediate_size": 4304,
	"is_encoder_decoder": false,
	"label2id": {
	"LABEL_0": 0,
	"LABEL_1": 1
	},
	"model_type": "qwen3_5",
	"num_heads": 16,
	"num_position_embeddings": 2304,
	"out_hidden_size": 4096,
	"output_attentions": false,
	"output_hidden_states": false,
	"patch_size": 16,
	"problem_type": null,
	"return_dict": true,
	"spatial_merge_size": 2,
	"temporal_patch_size": 2
	},
	"vision_end_token_id": 248054,
	"vision_start_token_id": 248053
	},
	"backbone_meta": {
	"backbone_path": "Qwen/Qwen3.5-9B",
	"backbone_type": "Qwen3_5"
	},
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 248044,
	"hidden_size": 4096,
	"memory_configs": {
	"alpha_max_fraction": 0.0,
	"alpha_max_tokens": 0,
	"alpha_min_tokens": 1,
	"alpha_top_p": 0.9,
	"commit_hidden_offset": 0,
	"forget_ratio": 1.0,
	"gated_delta_alpha_init": 1.0,
	"gated_delta_beta_init": 1.0,
	"gumbel_topk_noise": true,
	"mem_norm_init": 1.0,
	"metis_block_type": "NormedReweightLearnedQueryMetisBlock",
	"metis_hyper_memory_type": "StraightThroughAlphaTopPGatedDeltaRuleMetisHyperMemory",
	"metis_local_memory_type": "NormalizedDeltaNetMetisLocalMemory",
	"metis_reweight_gamma": 0.9,
	"pool_temperature": 1.0,
	"qk_kernel_type": "elu_plus_one",
	"stride_interval": 8,
	"uniform_num_selected": 16,
	"update_ratio": 0.9
	},
	"model_type": "metis",
	"num_attention_heads": 16,
	"num_hidden_layers": 32,
	"pad_token_id": null,
	"transformers_version": "5.4.0"
	}