Update tiny models for IdeficsForVisionText2Text

config.json

@@ -0,0 +1,77 @@
+{
+  "additional_vocab_size": 0,
+  "alpha_initializer": "ones",
+  "alpha_type": "float",
+  "alphas_initializer_range": 0.0,
+  "architectures": [
+    "IdeficsForVisionText2Text"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "cross_layer_interval": 1,
+  "dropout": 0.0,
+  "dtype": "float32",
+  "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": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 32,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "image_size": 30,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "is_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "modality_type_vocab_size": 2,
+  "model_type": "idefics",
+  "num_attention_heads": 4,
+  "num_channels": 3,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "patch_size": 2,
+  "perceiver_config": {
+    "model_type": "idefics_perciever",
+    "qk_layer_norms_perceiver": false,
+    "resampler_depth": 6,
+    "resampler_head_dim": 96,
+    "resampler_n_heads": 16,
+    "resampler_n_latents": 64,
+    "use_resampler": false
+  },
+  "qk_layer_norms": false,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "use_resampler": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "embed_dim": 32,
+    "hidden_act": "gelu",
+    "image_size": 30,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "layer_norm_eps": 1e-05,
+    "model_type": "idefics_vision",
+    "num_attention_heads": 4,
+    "num_channels": 3,
+    "num_hidden_layers": 2,
+    "patch_size": 2
+  },
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68158fc0f34cd0fad42849d88b8d931f10f552e093329a14f57e0839edb7a9c3
+size 8410928

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_num_channels": 3,
+  "image_processor_type": "IdeficsImageProcessor",
+  "image_size": 30,
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 30,
+    "width": 30
+  }
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<fake_token_around_image>",
+    "<image>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 512,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}