config.json

{
  "_name_or_path": "/fsx/miquel/smolvlmvideo/checkpoints/final-visionUnfrozen-balanced/checkpoint-6550",
  "architectures": [
    "SmolVLMForConditionalGeneration"
  ],
  "image_token_id": 49190,
  "model_type": "smolvlm",
  "pad_token_id": 128002,
  "scale_factor": 3,
  "text_config": {
    "_flash_attn_2_enabled": true,
    "_name_or_path": "None",
    "architectures": [
      "VLlama3ForCausalLM"
    ],
    "head_dim": 64,
    "hidden_size": 2048,
    "intermediate_size": 8192,
    "max_position_embeddings": 8192,
    "model_type": "llama",
    "neftune_noise_alpha": 0.0,
    "num_hidden_layers": 24,
    "pad_token_id": 2,
    "perceiver_config": {
      "_attn_implementation_autoset": false,
      "_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": "vllama3",
      "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": 6,
      "resampler_head_dim": 96,
      "resampler_n_heads": 16,
      "resampler_n_latents": 64,
      "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": "4.46.0",
      "typical_p": 1.0,
      "use_bfloat16": false
    },
    "pixel_shuffle_factor": 3,
    "qk_layer_norms": false,
    "rms_norm_eps": 1e-05,
    "rope_theta": 130000,
    "torch_dtype": "bfloat16",
    "transformers.js_config": {
      "kv_cache_dtype": {
        "fp16": "float16",
        "q4f16": "float16"
      }
    },
    "use_resampler": false,
    "vocab_size": 49280
  },
  "tie_word_embeddings": false,
  "torch_dtype": "float32",
  "transformers_version": "4.47.1",
  "use_cache": false,
  "use_reentrant_checkpointing": false,
  "vision_config": {
    "image_size": 384,
    "intermediate_size": 4304,
    "max_image_size": {
      "longest_edge": 384
    },
    "model_type": "smolvlm_vision",
    "num_hidden_layers": 27,
    "patch_size": 14,
    "size": {
      "longest_edge": 1920
    },
    "tie_word_embeddings": false,
    "use_base_siglip": false
  },
  "vocab_size": 49280
}