Instructions to use unsloth/Step-3.7-Flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/Step-3.7-Flash with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/Step-3.7-Flash", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("unsloth/Step-3.7-Flash", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/Step-3.7-Flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/Step-3.7-Flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/Step-3.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/Step-3.7-Flash

SGLang

How to use unsloth/Step-3.7-Flash 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 "unsloth/Step-3.7-Flash" \
    --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": "unsloth/Step-3.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "unsloth/Step-3.7-Flash" \
        --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": "unsloth/Step-3.7-Flash",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use unsloth/Step-3.7-Flash with Docker Model Runner:
```
docker model run hf.co/unsloth/Step-3.7-Flash
```

Step-3.7-Flash / config.json

danielhanchen

Upload folder using huggingface_hub

6c0b16e verified about 7 hours ago

raw

history blame contribute delete

7.62 kB

	{
	"architectures": [
	"Step3p7ForConditionalGeneration"
	],
	"auto_map": {
	"AutoConfig": "configuration_step3p7.Step3p7Config",
	"AutoModelForCausalLM": "modeling_step3p7.Step3p7ForConditionalGeneration",
	"AutoProcessor": "processing_step3.Step3VLProcessor"
	},
	"hidden_size": 4096,
	"im_end_token": "<im_end>",
	"im_patch_token": "<im_patch>",
	"im_start_token": "<im_start>",
	"image_token_id": 128001,
	"image_token_len": 169,
	"max_position_embeddings": 262144,
	"model_type": "step3p7",
	"pad_token_id": 2,
	"patch_token_len": 81,
	"projector_bias": false,
	"text_config": {
	"architectures": [
	"Step3p5ForCausalLM"
	],
	"att_impl_type": "GQA",
	"attention_dropout": 0.0,
	"attention_other_setting": {
	"attention_type": "sliding_attention",
	"head_dim": 128,
	"num_attention_groups": 8,
	"num_attention_heads": 96,
	"true_head_dim": 128
	},
	"bos_token_id": 0,
	"torch_dtype": "bfloat16",
	"eos_token_id": [
	1,
	2,
	128007
	],
	"head_dim": 128,
	"hidden_size": 4096,
	"intermediate_size": 11264,
	"layer_types": [
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention",
	"full_attention",
	"sliding_attention",
	"sliding_attention",
	"sliding_attention"
	],
	"max_position_embeddings": 262144,
	"max_seq_len": 262144,
	"model_type": "step3p5",
	"moe_every_n_layer": 1,
	"moe_intermediate_size": 1280,
	"moe_layer_offset": 0,
	"moe_layers_enum": "3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44",
	"moe_num_experts": 288,
	"moe_router_activation": "sigmoid",
	"moe_router_scaling_factor": 3.0,
	"moe_top_k": 8,
	"need_fp32_gate": true,
	"norm_expert_weight": true,
	"num_attention_groups": 8,
	"num_attention_heads": 64,
	"num_hidden_layers": 45,
	"num_nextn_predict_layers": 3,
	"pad_token_id": 1,
	"partial_rotary_factors": [
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0,
	0.5,
	1.0,
	1.0,
	1.0
	],
	"rms_norm_eps": 1e-05,
	"rope_parameters": {
	"factor": 2.0,
	"high_freq_factor": 32.0,
	"low_freq_factor": 1.0,
	"original_max_position_embeddings": 131072,
	"rope_theta": [
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0
	],
	"rope_type": "llama3"
	},
	"rope_theta": [
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0,
	5000000.0,
	10000.0,
	10000.0,
	10000.0
	],
	"share_expert_dim": 1280,
	"sink": false,
	"sliding_window": 512,
	"swiglu_limits": [
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	7,
	7,
	0.0,
	0.0,
	0.0
	],
	"swiglu_limits_shared": [
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	0.0,
	16,
	16,
	0.0,
	0.0,
	0.0
	],
	"use_head_wise_attn_gate": true,
	"use_mfa": false,
	"use_moe": true,
	"use_moe_router_bias": true,
	"use_qk_norm": false,
	"use_rope_layers": [],
	"vocab_size": 128896,
	"yarn_only_types": [
	"full_attention"
	]
	},
	"transformers_version": "5.10.0.dev0",
	"understand_projector_stride": 2,
	"unsloth_fixed": true,
	"use_im_start_end": "true",
	"vision_config": {
	"heads": 16,
	"hidden_act": "quick_gelu",
	"image_size": 728,
	"layer_norm_eps": 1e-05,
	"layers": 47,
	"ls_init_value": 0.1,
	"mlp_ratio": 5.833333333333333,
	"model_type": "perception_encoder",
	"num_channels": 3,
	"output_dim": null,
	"patch_size": 14,
	"pool_type": "none",
	"ues_cls_token": false,
	"use_abs_posemb": true,
	"use_cls_token": false,
	"use_ln_post": false,
	"use_ln_pre": true,
	"use_rope2d": true,
	"width": 1536
	},
	"vision_select_layer": -1
	}