Instructions to use bigai/GS1-9B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigai/GS1-9B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="bigai/GS1-9B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bigai/GS1-9B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from bigai/GS1-9B: direct link, hf CLI and curl.
- Browser
- Download file 3.79 kB
-
https://huggingface.co/bigai/GS1-9B/resolve/main/config.json
- Command line
-
hf download hf://bigai/GS1-9B/config.json
-
curl -L -o config.json https://huggingface.co/bigai/GS1-9B/resolve/main/config.json
3.79 kB
| { | |
| "architectures": [ | |
| "GS1Model" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modular_gs1.GS1Config", | |
| "AutoModel": "modular_gs1.GS1Model" | |
| }, | |
| "calibration": { | |
| "log_temperature_bound": 2.995732273553991, | |
| "mode": "identity" | |
| }, | |
| "decision": { | |
| "attnres": true, | |
| "attnres_eps": 1e-06, | |
| "attnres_layers": null, | |
| "bidirectional": true, | |
| "bidirectional_layers": null, | |
| "cross_attention_heads": 16, | |
| "cross_attention_layers": 2, | |
| "norm_eps": 1e-05, | |
| "projection_size": 2048 | |
| }, | |
| "dtype": "float32", | |
| "head_compute_dtype": "bfloat16", | |
| "image_token_id": 248056, | |
| "inference_limits": { | |
| "batch_tokens": 32768, | |
| "max_attention_bytes": 549755813888, | |
| "max_branches": 5120, | |
| "max_context": 32768, | |
| "max_logit_elements": 16777216, | |
| "max_questions": 512, | |
| "max_request_tokens": 131072 | |
| }, | |
| "initialization_seed": 41, | |
| "model_type": "gs1", | |
| "release_date": "2026-11-10", | |
| "structural_token_ids": { | |
| "</option>": 248082, | |
| "</question>": 248080, | |
| "</state>": 248078, | |
| "<option>": 248081, | |
| "<question>": 248079, | |
| "<state>": 248077, | |
| "<|decide|>": 248083 | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_output_gate": true, | |
| "bos_token_id": null, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 248044, | |
| "full_attention_interval": 4, | |
| "head_dim": 256, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "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, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.25, | |
| "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": false, | |
| "vocab_size": 248320 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.3.0", | |
| "video_token_id": 248057, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [], | |
| "depth": 27, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "qwen3_5", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 4096, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "vision_end_token_id": 248054, | |
| "vision_start_token_id": 248053 | |
| } | |