Upload Idefics3ForConditionalGeneration

config.json

@@ -7,42 +7,143 @@
   "pad_token_id": 128002,
   "scale_factor": 2,
   "text_config": {
+    "_flash_attn_2_enabled": true,
+    "_name_or_path": "None",
+    "architectures": [
+      "Idefics3ForVisionText2Text"
+    ],
     "attention_bias": false,
     "attention_dropout": 0.0,
-    "head_dim": 4,
+    "auto_map": {
+      "AutoConfig": "configuration_idefics3.Idefics3Config",
+      "AutoModelForCausalLM": "modeling_idefics3.Idefics3ForVisionText2Text"
+    },
+    "bos_token_id": 128000,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 16,
     "initializer_range": 0.02,
-    "intermediate_size": 32,
-    "max_position_embeddings": 2048,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 131072,
     "mlp_bias": false,
     "model_type": "llama",
+    "neftune_noise_alpha": 0.0,
     "num_attention_heads": 4,
     "num_hidden_layers": 2,
     "num_key_value_heads": 2,
+    "pad_token_id": 128002,
+    "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": "idefics3",
+      "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": 128002,
+      "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": "4.43.2",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
     "pretraining_tp": 1,
-    "rms_norm_eps": 1e-06,
-    "rope_scaling": null,
-    "rope_theta": 10000.0,
+    "qk_layer_norms": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "torch_dtype": "bfloat16",
     "use_cache": true,
+    "use_resampler": false,
     "vocab_size": 128259
   },
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.56.0.dev0",
   "use_cache": true,
   "vision_config": {
     "attention_dropout": 0.0,
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 16,
-    "image_size": 224,
+    "image_size": 364,
     "initializer_range": 0.02,
-    "intermediate_size": 32,
+    "intermediate_size": 4304,
     "layer_norm_eps": 1e-06,
     "model_type": "idefics3_vision",
     "num_attention_heads": 4,
     "num_channels": 3,
     "num_hidden_layers": 2,
-    "patch_size": 32
+    "num_key_value_heads": 2,
+    "old_vision_model_name": "/fsx/hugo/siglip-so400m-14-364-flash-attn2-navit",
+    "pad_token_id": 128002,
+    "patch_size": 14
   }
 }

generation_config.json

@@ -1,7 +1,11 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "pad_token_id": 128002,
   "transformers_version": "4.56.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7b437fd28bcbaf93e52dd6758b46b53758fbc085f7ba9af89cf8d65b435b3a
-size 16664800
+oid sha256:da631b250a2511e3aec1519afb448683bc565b40461c68122ebeb50e133760bc
+size 11682096