First commit

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<fake_token_around_image>": 32000,
+  "<image>": 32001
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "None",
+  "additional_vocab_size": 2,
+  "alpha_initializer": "zeros",
+  "alpha_type": "float",
+  "alphas_initializer_range": 0.0,
+  "architectures": [
+    "VLlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "cross_layer_activation_function": "swiglu",
+  "cross_layer_interval": 4,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "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": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "model_type": "vllama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "qk_layer_norms": true,
+  "qk_layer_norms_perceiver": true,
+  "resampler_depth": 6,
+  "resampler_head_dim": 96,
+  "resampler_n_heads": 16,
+  "resampler_n_latents": 64,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.28.0.dev0",
+  "use_cache": true,
+  "use_resampler": true,
+  "vision_embed_dim": 1280,
+  "vision_image_size": 224,
+  "vision_model_name": "laion/CLIP-ViT-H-14-laion2B-s32B-b79K",
+  "vision_model_params": "{\"id2label\":{}, \"label2id\":{}}",
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa56e10990afb6b882003571f094c95e37fae5471c4d8a318c7368644261ecb5
+size 9971911147

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de33759f4bbb32b1c56bd7d891ab0966380e55d6a830afc87cc136a8e60513b
+size 7887831155

special_tokens_map.json

@@ -0,0 +1,40 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<fake_token_around_image>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "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 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 2048,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/Users/leotronchon/.cache/huggingface/hub/models--huggyllama--llama-7b/snapshots/8416d3fefb0cb3ff5775a7b13c1692d10ff1aa16/special_tokens_map.json",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}