Instructions to use hf-internal-testing/tiny-random-step3p7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-internal-testing/tiny-random-step3p7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="hf-internal-testing/tiny-random-step3p7")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("hf-internal-testing/tiny-random-step3p7", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use hf-internal-testing/tiny-random-step3p7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "hf-internal-testing/tiny-random-step3p7" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hf-internal-testing/tiny-random-step3p7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/hf-internal-testing/tiny-random-step3p7
- SGLang
How to use hf-internal-testing/tiny-random-step3p7 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 "hf-internal-testing/tiny-random-step3p7" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hf-internal-testing/tiny-random-step3p7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "hf-internal-testing/tiny-random-step3p7" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "hf-internal-testing/tiny-random-step3p7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use hf-internal-testing/tiny-random-step3p7 with Docker Model Runner:
docker model run hf.co/hf-internal-testing/tiny-random-step3p7
| { | |
| "architectures": [ | |
| "Step3p7ForConditionalGeneration" | |
| ], | |
| "dtype": "float32", | |
| "image_token_id": 63, | |
| "model_type": "step3p7", | |
| "projector_bias": false, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "eos_token_id": 2, | |
| "gating": true, | |
| "head_dim": 8, | |
| "hidden_act": "silu", | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 88, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "max_position_embeddings": 262144, | |
| "mlp_bias": false, | |
| "mlp_layer_types": [ | |
| "dense", | |
| "dense", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse", | |
| "sparse" | |
| ], | |
| "model_type": "step3p5", | |
| "moe_intermediate_size": 10, | |
| "moe_router_scaling_factor": 3.0, | |
| "n_routed_experts": 8, | |
| "num_attention_heads": 8, | |
| "num_attention_heads_per_layer": [ | |
| 8, | |
| 12, | |
| 12, | |
| 12, | |
| 8, | |
| 12, | |
| 12, | |
| 12 | |
| ], | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 2, | |
| "num_nextn_predict_layers": 0, | |
| "num_sliding_attention_heads": 12, | |
| "pad_token_id": 1, | |
| "query_pre_attn_scalar": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "factor": 2.0, | |
| "high_freq_factor": 32.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 131072, | |
| "partial_rotary_factor": 0.5, | |
| "rope_theta": 5000000.0, | |
| "rope_type": "llama3" | |
| }, | |
| "sliding_attention": { | |
| "partial_rotary_factor": 1.0, | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "share_expert_dim": 10, | |
| "sliding_window": 6, | |
| "swiglu_limits": [ | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| 7, | |
| 7 | |
| ], | |
| "swiglu_limits_shared": [ | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| null, | |
| 16, | |
| 16 | |
| ], | |
| "tie_word_embeddings": false, | |
| "use_cache": true, | |
| "vocab_size": 64 | |
| }, | |
| "transformers_version": "5.15.0.dev0", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "hidden_act": "quick_gelu", | |
| "hidden_size": 16, | |
| "image_size": 16, | |
| "intermediate_size": 93, | |
| "layer_norm_eps": 1e-05, | |
| "layer_scale_init_value": 0.1, | |
| "max_position_embeddings": 16, | |
| "mlp_ratio": 5.833333333333333, | |
| "model_type": "step3p5_vision", | |
| "num_attention_heads": 4, | |
| "num_channels": 3, | |
| "num_hidden_layers": 2, | |
| "patch_size": 4, | |
| "rope_parameters": { | |
| "rope_theta": 10000.0, | |
| "rope_type": "default" | |
| } | |
| } | |
| } | |