Hugging Face's logo

mlx-community
/
command-a-vision-07-2025-4bit

Image-Text-to-Text
Transformers
Safetensors
MLX
cohere2_vision
conversational
4-bit precision
Model card Files
xet
Community
command-a-vision-07-2025-4bit / config.json
prince-canuma's picture
prince-canuma
Upload folder using huggingface_hub
8864bb5 verified
raw
history blame contribute delete
9.62 kB
 {
"adapter_layer_norm_eps": 1e-06,
"add_cross_attention": false,
"alignment_activation_fn": "swiglu",
"alignment_intermediate_size": 36864,
"architectures": [
"Cohere2VisionForConditionalGeneration"
],
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"downsample_factor": 2,
"early_stopping": false,
"enable_adapter_layer_norm": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"image_token": 255036,
"image_token_id": 255036,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"max_splits_per_img": 12,
"min_length": 0,
"model_type": "cohere2_vision",
"no_repeat_ngram_size": 0,
"num_beam_groups": 1,
"num_beams": 1,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": null,
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"quantization": {
"group_size": 64,
"bits": 4
},
"quantization_config": {
"group_size": 64,
"bits": 4
},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"text_config": {
"vocab_size": 256000,
"max_position_embeddings": 500000,
"hidden_size": 12288,
"logit_scale": 1.0,
"intermediate_size": 36864,
"num_hidden_layers": 64,
"num_attention_heads": 96,
"num_key_value_heads": 8,
"hidden_act": "silu",
"initializer_range": 0.02,
"layer_norm_eps": 1e-05,
"use_cache": true,
"rope_theta": 50000,
"rope_scaling": null,
"attention_bias": false,
"attention_dropout": 0.0,
"sliding_window": 4096,
"layer_types": [
"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",
"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"
],
"head_dim": 128,
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"torch_dtype": null,
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"architectures": [
"Cohere2ForCausalLM"
],
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"task_specific_params": null,
"problem_type": null,
"tokenizer_class": null,
"prefix": null,
"bos_token_id": 5,
"pad_token_id": 0,
"eos_token_id": 255001,
"sep_token_id": null,
"decoder_start_token_id": null,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"_name_or_path": "",
"_sliding_window_pattern": 4,
"cache_implementation": "hybrid",
"layer_switch": 4,
"model_type": "cohere2",
"order_of_interleaved_layers": "local_attn_first",
"position_embedding_type": "rope_gptj",
"rotary_pct": 1.0,
"use_embedding_sharing": true,
"use_gated_activation": true,
"use_parallel_block": true,
"use_parallel_embedding": true,
"use_qk_norm": false,
"tf_legacy_loss": false,
"use_bfloat16": false,
"output_attentions": false
},
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"transformers_version": "4.55.2",
"typical_p": 1.0,
"use_bfloat16": false,
"vision_config": {
"return_dict": true,
"output_hidden_states": false,
"torchscript": false,
"torch_dtype": null,
"pruned_heads": {},
"tie_word_embeddings": true,
"chunk_size_feed_forward": 0,
"is_encoder_decoder": false,
"is_decoder": false,
"cross_attention_hidden_size": null,
"add_cross_attention": false,
"tie_encoder_decoder": false,
"architectures": null,
"finetuning_task": null,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"task_specific_params": null,
"problem_type": null,
"tokenizer_class": null,
"prefix": null,
"bos_token_id": null,
"pad_token_id": null,
"eos_token_id": null,
"sep_token_id": null,
"decoder_start_token_id": null,
"max_length": 20,
"min_length": 0,
"do_sample": false,
"early_stopping": false,
"num_beams": 1,
"num_beam_groups": 1,
"diversity_penalty": 0.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"typical_p": 1.0,
"repetition_penalty": 1.0,
"length_penalty": 1.0,
"no_repeat_ngram_size": 0,
"encoder_no_repeat_ngram_size": 0,
"bad_words_ids": null,
"num_return_sequences": 1,
"output_scores": false,
"return_dict_in_generate": false,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"remove_invalid_values": false,
"exponential_decay_length_penalty": null,
"suppress_tokens": null,
"begin_suppress_tokens": null,
"_name_or_path": "",
"model_type": "siglip_vision_model",
"vision_use_head": false,
"tf_legacy_loss": false,
"use_bfloat16": false,
"hidden_size": 1152,
"intermediate_size": 4304,
"num_hidden_layers": 27,
"num_attention_heads": 16,
"num_channels": 3,
"patch_size": 16,
"image_size": 512,
"attention_dropout": 0.0,
"layer_norm_eps": 1e-06,
"hidden_act": "gelu_pytorch_tanh",
"output_attentions": false
},
"vision_feature_layer": -1,
"vision_feature_select_strategy": "full"
}