Video-Text-to-Text
Transformers
Safetensors
English
Chinese
moss_vl
feature-extraction
MOSS-VL
image-understanding
video-understanding
FP8
compressed-tensors
quantized
SGLang
custom_code
Instructions to use OpenMOSS-Team/MOSS-VL-Instruct-0708-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenMOSS-Team/MOSS-VL-Instruct-0708-FP8 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OpenMOSS-Team/MOSS-VL-Instruct-0708-FP8", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "MossVLForConditionalGeneration" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_moss_vl.MossVLConfig", | |
| "AutoModel": "modeling_moss_vl.MossVLForConditionalGeneration", | |
| "AutoModelForCausalLM": "modeling_moss_vl.MossVLForConditionalGeneration" | |
| }, | |
| "dtype": "bfloat16", | |
| "image_token_id": 151655, | |
| "model_type": "moss_vl", | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "format": "float-quantized", | |
| "input_activations": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": true, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": null, | |
| "observer_kwargs": {}, | |
| "scale_dtype": null, | |
| "strategy": "token", | |
| "symmetric": true, | |
| "type": "float", | |
| "zp_dtype": null | |
| }, | |
| "output_activations": null, | |
| "targets": [ | |
| "re:^model\\.language_model\\.layers\\.(0|1|3|4|5|7|8|9|11|12|13|15|16|17|19|20|21|23|24|25|27|28|29|31|32|33|35|36|37|39|40|41|43|44|45|47)\\.(self_attn\\.(q_proj|k_proj|v_proj|o_proj)|mlp\\.(gate_proj|up_proj|down_proj))$", | |
| "re:^model\\.language_model\\.model\\.layers\\.(0|1|3|4|5|7|8|9|11|12|13|15|16|17|19|20|21|23|24|25|27|28|29|31|32|33|35|36|37|39|40|41|43|44|45|47)\\.(self_attn\\.(q_proj|k_proj|v_proj|qkv_proj|o_proj)|mlp\\.(gate_proj|up_proj|gate_up_proj|down_proj))$" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "memoryless_minmax", | |
| "observer_kwargs": {}, | |
| "scale_dtype": null, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "float", | |
| "zp_dtype": null | |
| } | |
| } | |
| }, | |
| "format": "float-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "model.visual.blocks.0.attn.qkv", | |
| "model.visual.blocks.0.attn.proj", | |
| "model.visual.blocks.0.mlp.linear_fc1", | |
| "model.visual.blocks.0.mlp.linear_fc2", | |
| "model.visual.blocks.1.attn.qkv", | |
| "model.visual.blocks.1.attn.proj", | |
| "model.visual.blocks.1.mlp.linear_fc1", | |
| "model.visual.blocks.1.mlp.linear_fc2", | |
| "model.visual.blocks.2.attn.qkv", | |
| "model.visual.blocks.2.attn.proj", | |
| "model.visual.blocks.2.mlp.linear_fc1", | |
| "model.visual.blocks.2.mlp.linear_fc2", | |
| "model.visual.blocks.3.attn.qkv", | |
| "model.visual.blocks.3.attn.proj", | |
| "model.visual.blocks.3.mlp.linear_fc1", | |
| "model.visual.blocks.3.mlp.linear_fc2", | |
| "model.visual.blocks.4.attn.qkv", | |
| "model.visual.blocks.4.attn.proj", | |
| "model.visual.blocks.4.mlp.linear_fc1", | |
| "model.visual.blocks.4.mlp.linear_fc2", | |
| "model.visual.blocks.5.attn.qkv", | |
| "model.visual.blocks.5.attn.proj", | |
| "model.visual.blocks.5.mlp.linear_fc1", | |
| "model.visual.blocks.5.mlp.linear_fc2", | |
| "model.visual.blocks.6.attn.qkv", | |
| "model.visual.blocks.6.attn.proj", | |
| "model.visual.blocks.6.mlp.linear_fc1", | |
| "model.visual.blocks.6.mlp.linear_fc2", | |
| "model.visual.blocks.7.attn.qkv", | |
| "model.visual.blocks.7.attn.proj", | |
| "model.visual.blocks.7.mlp.linear_fc1", | |
| "model.visual.blocks.7.mlp.linear_fc2", | |
| "model.visual.blocks.8.attn.qkv", | |
| "model.visual.blocks.8.attn.proj", | |
| "model.visual.blocks.8.mlp.linear_fc1", | |
| "model.visual.blocks.8.mlp.linear_fc2", | |
| "model.visual.blocks.9.attn.qkv", | |
| "model.visual.blocks.9.attn.proj", | |
| "model.visual.blocks.9.mlp.linear_fc1", | |
| "model.visual.blocks.9.mlp.linear_fc2", | |
| "model.visual.blocks.10.attn.qkv", | |
| "model.visual.blocks.10.attn.proj", | |
| "model.visual.blocks.10.mlp.linear_fc1", | |
| "model.visual.blocks.10.mlp.linear_fc2", | |
| "model.visual.blocks.11.attn.qkv", | |
| "model.visual.blocks.11.attn.proj", | |
| "model.visual.blocks.11.mlp.linear_fc1", | |
| "model.visual.blocks.11.mlp.linear_fc2", | |
| "model.visual.blocks.12.attn.qkv", | |
| "model.visual.blocks.12.attn.proj", | |
| "model.visual.blocks.12.mlp.linear_fc1", | |
| "model.visual.blocks.12.mlp.linear_fc2", | |
| "model.visual.blocks.13.attn.qkv", | |
| "model.visual.blocks.13.attn.proj", | |
| "model.visual.blocks.13.mlp.linear_fc1", | |
| "model.visual.blocks.13.mlp.linear_fc2", | |
| "model.visual.blocks.14.attn.qkv", | |
| "model.visual.blocks.14.attn.proj", | |
| "model.visual.blocks.14.mlp.linear_fc1", | |
| "model.visual.blocks.14.mlp.linear_fc2", | |
| "model.visual.blocks.15.attn.qkv", | |
| "model.visual.blocks.15.attn.proj", | |
| "model.visual.blocks.15.mlp.linear_fc1", | |
| "model.visual.blocks.15.mlp.linear_fc2", | |
| "model.visual.blocks.16.attn.qkv", | |
| "model.visual.blocks.16.attn.proj", | |
| "model.visual.blocks.16.mlp.linear_fc1", | |
| "model.visual.blocks.16.mlp.linear_fc2", | |
| "model.visual.blocks.17.attn.qkv", | |
| "model.visual.blocks.17.attn.proj", | |
| "model.visual.blocks.17.mlp.linear_fc1", | |
| "model.visual.blocks.17.mlp.linear_fc2", | |
| "model.visual.blocks.18.attn.qkv", | |
| "model.visual.blocks.18.attn.proj", | |
| "model.visual.blocks.18.mlp.linear_fc1", | |
| "model.visual.blocks.18.mlp.linear_fc2", | |
| "model.visual.blocks.19.attn.qkv", | |
| "model.visual.blocks.19.attn.proj", | |
| "model.visual.blocks.19.mlp.linear_fc1", | |
| "model.visual.blocks.19.mlp.linear_fc2", | |
| "model.visual.blocks.20.attn.qkv", | |
| "model.visual.blocks.20.attn.proj", | |
| "model.visual.blocks.20.mlp.linear_fc1", | |
| "model.visual.blocks.20.mlp.linear_fc2", | |
| "model.visual.blocks.21.attn.qkv", | |
| "model.visual.blocks.21.attn.proj", | |
| "model.visual.blocks.21.mlp.linear_fc1", | |
| "model.visual.blocks.21.mlp.linear_fc2", | |
| "model.visual.blocks.22.attn.qkv", | |
| "model.visual.blocks.22.attn.proj", | |
| "model.visual.blocks.22.mlp.linear_fc1", | |
| "model.visual.blocks.22.mlp.linear_fc2", | |
| "model.visual.blocks.23.attn.qkv", | |
| "model.visual.blocks.23.attn.proj", | |
| "model.visual.blocks.23.mlp.linear_fc1", | |
| "model.visual.blocks.23.mlp.linear_fc2", | |
| "model.visual.blocks.24.attn.qkv", | |
| "model.visual.blocks.24.attn.proj", | |
| "model.visual.blocks.24.mlp.linear_fc1", | |
| "model.visual.blocks.24.mlp.linear_fc2", | |
| "model.visual.blocks.25.attn.qkv", | |
| "model.visual.blocks.25.attn.proj", | |
| "model.visual.blocks.25.mlp.linear_fc1", | |
| "model.visual.blocks.25.mlp.linear_fc2", | |
| "model.visual.blocks.26.attn.qkv", | |
| "model.visual.blocks.26.attn.proj", | |
| "model.visual.blocks.26.mlp.linear_fc1", | |
| "model.visual.blocks.26.mlp.linear_fc2", | |
| "model.visual.merger.linear_fc1", | |
| "model.visual.merger.linear_fc2", | |
| "model.language_model.layers.2.cross_attn.q_proj", | |
| "model.language_model.layers.2.cross_attn.k_proj", | |
| "model.language_model.layers.2.cross_attn.v_proj", | |
| "model.language_model.layers.2.cross_attn.o_proj", | |
| "model.language_model.layers.2.mlp.gate_proj", | |
| "model.language_model.layers.2.mlp.up_proj", | |
| "model.language_model.layers.2.mlp.down_proj", | |
| "model.language_model.layers.6.cross_attn.q_proj", | |
| "model.language_model.layers.6.cross_attn.k_proj", | |
| "model.language_model.layers.6.cross_attn.v_proj", | |
| "model.language_model.layers.6.cross_attn.o_proj", | |
| "model.language_model.layers.6.mlp.gate_proj", | |
| "model.language_model.layers.6.mlp.up_proj", | |
| "model.language_model.layers.6.mlp.down_proj", | |
| "model.language_model.layers.10.cross_attn.q_proj", | |
| "model.language_model.layers.10.cross_attn.k_proj", | |
| "model.language_model.layers.10.cross_attn.v_proj", | |
| "model.language_model.layers.10.cross_attn.o_proj", | |
| "model.language_model.layers.10.mlp.gate_proj", | |
| "model.language_model.layers.10.mlp.up_proj", | |
| "model.language_model.layers.10.mlp.down_proj", | |
| "model.language_model.layers.14.cross_attn.q_proj", | |
| "model.language_model.layers.14.cross_attn.k_proj", | |
| "model.language_model.layers.14.cross_attn.v_proj", | |
| "model.language_model.layers.14.cross_attn.o_proj", | |
| "model.language_model.layers.14.mlp.gate_proj", | |
| "model.language_model.layers.14.mlp.up_proj", | |
| "model.language_model.layers.14.mlp.down_proj", | |
| "model.language_model.layers.18.cross_attn.q_proj", | |
| "model.language_model.layers.18.cross_attn.k_proj", | |
| "model.language_model.layers.18.cross_attn.v_proj", | |
| "model.language_model.layers.18.cross_attn.o_proj", | |
| "model.language_model.layers.18.mlp.gate_proj", | |
| "model.language_model.layers.18.mlp.up_proj", | |
| "model.language_model.layers.18.mlp.down_proj", | |
| "model.language_model.layers.22.cross_attn.q_proj", | |
| "model.language_model.layers.22.cross_attn.k_proj", | |
| "model.language_model.layers.22.cross_attn.v_proj", | |
| "model.language_model.layers.22.cross_attn.o_proj", | |
| "model.language_model.layers.22.mlp.gate_proj", | |
| "model.language_model.layers.22.mlp.up_proj", | |
| "model.language_model.layers.22.mlp.down_proj", | |
| "model.language_model.layers.26.cross_attn.q_proj", | |
| "model.language_model.layers.26.cross_attn.k_proj", | |
| "model.language_model.layers.26.cross_attn.v_proj", | |
| "model.language_model.layers.26.cross_attn.o_proj", | |
| "model.language_model.layers.26.mlp.gate_proj", | |
| "model.language_model.layers.26.mlp.up_proj", | |
| "model.language_model.layers.26.mlp.down_proj", | |
| "model.language_model.layers.30.cross_attn.q_proj", | |
| "model.language_model.layers.30.cross_attn.k_proj", | |
| "model.language_model.layers.30.cross_attn.v_proj", | |
| "model.language_model.layers.30.cross_attn.o_proj", | |
| "model.language_model.layers.30.mlp.gate_proj", | |
| "model.language_model.layers.30.mlp.up_proj", | |
| "model.language_model.layers.30.mlp.down_proj", | |
| "model.language_model.layers.34.cross_attn.q_proj", | |
| "model.language_model.layers.34.cross_attn.k_proj", | |
| "model.language_model.layers.34.cross_attn.v_proj", | |
| "model.language_model.layers.34.cross_attn.o_proj", | |
| "model.language_model.layers.34.mlp.gate_proj", | |
| "model.language_model.layers.34.mlp.up_proj", | |
| "model.language_model.layers.34.mlp.down_proj", | |
| "model.language_model.layers.38.cross_attn.q_proj", | |
| "model.language_model.layers.38.cross_attn.k_proj", | |
| "model.language_model.layers.38.cross_attn.v_proj", | |
| "model.language_model.layers.38.cross_attn.o_proj", | |
| "model.language_model.layers.38.mlp.gate_proj", | |
| "model.language_model.layers.38.mlp.up_proj", | |
| "model.language_model.layers.38.mlp.down_proj", | |
| "model.language_model.layers.42.cross_attn.q_proj", | |
| "model.language_model.layers.42.cross_attn.k_proj", | |
| "model.language_model.layers.42.cross_attn.v_proj", | |
| "model.language_model.layers.42.cross_attn.o_proj", | |
| "model.language_model.layers.42.mlp.gate_proj", | |
| "model.language_model.layers.42.mlp.up_proj", | |
| "model.language_model.layers.42.mlp.down_proj", | |
| "model.language_model.layers.46.cross_attn.q_proj", | |
| "model.language_model.layers.46.cross_attn.k_proj", | |
| "model.language_model.layers.46.cross_attn.v_proj", | |
| "model.language_model.layers.46.cross_attn.o_proj", | |
| "model.language_model.layers.46.mlp.gate_proj", | |
| "model.language_model.layers.46.mlp.up_proj", | |
| "model.language_model.layers.46.mlp.down_proj", | |
| "lm_head", | |
| "re:^model\\.visual\\.", | |
| "re:^model\\.language_model\\.model\\.layers\\.(2|6|10|14|18|22|26|30|34|38|42|46)\\.", | |
| "model.language_model.lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed", | |
| "sparsity_config": {}, | |
| "transform_config": {}, | |
| "version": "0.14.0", | |
| "packed_modules_mapping": { | |
| "qkv_proj": [ | |
| "q_proj", | |
| "k_proj", | |
| "v_proj" | |
| ], | |
| "gate_up_proj": [ | |
| "gate_proj", | |
| "up_proj" | |
| ] | |
| } | |
| }, | |
| "text_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "cross_attention_layers": [ | |
| 2, | |
| 6, | |
| 10, | |
| 14, | |
| 18, | |
| 22, | |
| 26, | |
| 30, | |
| 34, | |
| 38, | |
| 42, | |
| 46 | |
| ], | |
| "dtype": "bfloat16", | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "max_position_embeddings": 262144, | |
| "model_type": "moss_vl_text", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "use_cache": true, | |
| "vocab_size": 151936 | |
| }, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "deepstack_visual_indexes": [ | |
| 8, | |
| 16, | |
| 24 | |
| ], | |
| "depth": 27, | |
| "dtype": "bfloat16", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "in_channels": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "model_type": "moss_vl_vision", | |
| "num_heads": 16, | |
| "num_position_embeddings": 2304, | |
| "out_hidden_size": 4096, | |
| "patch_size": 16, | |
| "spatial_merge_size": 2, | |
| "temporal_patch_size": 1 | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_seq_pad_multiple": 8, | |
| "vision_start_token_id": 151652 | |
| } | |