Instructions to use Spiteman/GLM-4.6V-Flash-oQ4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Spiteman/GLM-4.6V-Flash-oQ4 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir GLM-4.6V-Flash-oQ4 Spiteman/GLM-4.6V-Flash-oQ4
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "architectures": [ | |
| "Glm4vForConditionalGeneration" | |
| ], | |
| "image_end_token_id": 151340, | |
| "image_start_token_id": 151339, | |
| "image_token_id": 151363, | |
| "model_type": "glm4v", | |
| "text_config": { | |
| "attention_bias": true, | |
| "attention_dropout": 0.0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": [ | |
| 151329, | |
| 151336, | |
| 151338 | |
| ], | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13696, | |
| "max_position_embeddings": 131072, | |
| "model_type": "glm4v_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 2, | |
| "pad_token_id": 151329, | |
| "rms_norm_eps": 1e-05, | |
| "rope_parameters": { | |
| "mrope_section": [ | |
| 8, | |
| 12, | |
| 12 | |
| ], | |
| "partial_rotary_factor": 0.5, | |
| "rope_theta": 500000, | |
| "rope_type": "default" | |
| }, | |
| "use_cache": true, | |
| "vocab_size": 151552 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.0.0rc0", | |
| "video_end_token_id": 151342, | |
| "video_start_token_id": 151341, | |
| "video_token_id": 151364, | |
| "vision_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "depth": 24, | |
| "hidden_act": "silu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 1536, | |
| "image_size": 336, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13696, | |
| "model_type": "glm4v_vision", | |
| "num_heads": 12, | |
| "out_hidden_size": 4096, | |
| "patch_size": 14, | |
| "rms_norm_eps": 1e-05, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 2 | |
| }, | |
| "eos_token_id": [ | |
| 151329, | |
| 151336, | |
| 151338, | |
| 151348 | |
| ], | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "mode": "affine", | |
| "language_model.model.layers.0.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.0.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.1.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.2.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.3.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.mlp.down_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.q_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.4.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.10.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.11.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.12.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.13.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.14.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.15.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.16.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.17.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.5.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.6.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.7.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.8.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.9.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.18.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.19.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.20.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.mlp.down_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.21.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.22.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.23.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.24.self_attn.o_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.k_proj": { | |
| "bits": 5, | |
| "group_size": 64, | |
| "mode": "affine" | |
| }, | |
| "language_model.model.layers.35.self_attn.v_proj": { | |
| "bits": 6, | |
| "group_size": 64, | |
| "mode": "affine" | |
| } | |
| } | |
| } |