Upload 10 files

.gitattributes

@@ -25,7 +25,6 @@
 *.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
 *.wasm filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 32001
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "additional_vocab_size": 2,
+  "alpha_initializer": "ones",
+  "alpha_type": "vector",
+  "alphas_initializer_range": 0.0,
+  "architectures": [
+    "IdeficsForVisionText2Text"
+  ],
+  "bos_token_id": 1,
+  "cross_layer_activation_function": "swiglu",
+  "cross_layer_interval": 1,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "ffn_dim": 64,
+  "freeze_lm_head": false,
+  "freeze_text_layers": false,
+  "freeze_text_module_exceptions": [],
+  "freeze_vision_layers": false,
+  "freeze_vision_module_exceptions": [],
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_new_tokens": 128,
+  "max_position_embeddings": 128,
+  "model_type": "idefics",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "qk_layer_norms": false,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.0.dev0",
+  "use_cache": true,
+  "use_resampler": true,
+  "vocab_size": 32000,
+  "word_embed_proj_dim": 16,
+  "vision_config": {
+    "hidden_act": "gelu",
+    "embed_dim": 32,
+    "image_size": 30,
+    "intermediate_size": 37,
+    "patch_size": 2,
+    "num_attention_heads": 4,
+    "num_hidden_layers": 5,
+    "vision_model_name": "hf-internal-testing/tiny-random-clip"
+  },
+  "perceiver_config": {
+    "qk_layer_norms_perceiver": false,
+    "resampler_depth": 2,
+    "resampler_head_dim": 8,
+    "resampler_n_heads": 2,
+    "resampler_n_latents": 16
+  }
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_new_tokens": 100,
+  "pad_token_id": 0,
+  "transformers_version": "4.27.0.dev0"
+}

preprocessor_config.json

@@ -0,0 +1,16 @@
+{
+  "image_num_channels": 3,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "IdeficsImageProcessor",
+  "image_size": 30,
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "IdeficsProcessor"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f5de05e77b318f3a80f79e1a8d6b1eda26841ecfd9c0afc4c38a2d14b4e6a5
+size 6467421

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<image>",
+    "<fake_token_around_image>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<image>",
+    "<fake_token_around_image>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}