config.json

{
  "_commit_hash": null,
  "_flash_attn_2_enabled": false,
  "additional_vocab_size": 2,
  "alpha_initializer": "zeros",
  "alpha_type": "float",
  "alphas_initializer_range": 0.0,
  "architectures": [
    "VMistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "cross_layer_interval": 1,
  "eos_token_id": 2,
  "freeze_lm_head": false,
  "freeze_text_layers": true,
  "freeze_text_module_exceptions": [],
  "freeze_vision_layers": true,
  "freeze_vision_module_exceptions": [],
  "hidden_act": "silu",
  "hidden_size": 16,
  "image_token_id": 32001,
  "initializer_range": 0.02,
  "intermediate_size": 64,
  "max_new_tokens": 100,
  "max_position_embeddings": 128,
  "model_type": "vmistral",
  "neftune_noise_alpha": 0.0,
  "num_attention_heads": 4,
  "num_hidden_layers": 2,
  "num_key_value_heads": 1,
  "pad_token_id": 0,
  "perceiver_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "attention_dropout": 0.0,
    "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,
    "early_stopping": 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,
    "hidden_act": "silu",
    "id2label": {
      "0": "LABEL_0",
      "1": "LABEL_1"
    },
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "vmistral",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_key_value_heads": 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": {},
    "qk_layer_norms_perceiver": false,
    "remove_invalid_values": false,
    "repetition_penalty": 1.0,
    "resampler_depth": 2,
    "resampler_head_dim": 8,
    "resampler_n_heads": 2,
    "resampler_n_latents": 16,
    "return_dict": true,
    "return_dict_in_generate": false,
    "sep_token_id": null,
    "suppress_tokens": null,
    "task_specific_params": null,
    "temperature": 1.0,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.37.1",
    "typical_p": 1.0,
    "use_bfloat16": false
  },
  "qk_layer_norms": false,
  "rms_norm_eps": 1e-06,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": null,
  "use_cache": true,
  "use_resampler": true,
  "vision_config": {
    "_name_or_path": "",
    "add_cross_attention": false,
    "architectures": null,
    "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,
    "early_stopping": false,
    "embed_dim": 144,
    "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_size": 30,
    "intermediate_size": 538,
    "is_decoder": false,
    "is_encoder_decoder": false,
    "label2id": {
      "LABEL_0": 0,
      "LABEL_1": 1
    },
    "length_penalty": 1.0,
    "max_length": 20,
    "min_length": 0,
    "model_type": "vmistral",
    "no_repeat_ngram_size": 0,
    "num_beam_groups": 1,
    "num_beams": 1,
    "num_hidden_layers": 3,
    "num_return_sequences": 1,
    "output_attentions": false,
    "output_hidden_states": false,
    "output_scores": false,
    "pad_token_id": null,
    "patch_size": 2,
    "prefix": null,
    "problem_type": null,
    "pruned_heads": {},
    "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,
    "tf_legacy_loss": false,
    "tie_encoder_decoder": false,
    "tie_word_embeddings": true,
    "tokenizer_class": null,
    "top_k": 50,
    "top_p": 1.0,
    "torch_dtype": null,
    "torchscript": false,
    "transformers_version": "4.37.1",
    "typical_p": 1.0,
    "use_bfloat16": false,
    "vision_model_name": "HuggingFaceM4/tiny-random-siglip"
  },
  "vocab_size": 32000
}