Upload folder using huggingface_hub

README.md

@@ -0,0 +1 @@
+Copied from katuni4ka/tiny-random-llava-next

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{ '<<SYS>>\n' + message['content'][0]['text'] + '\n<</SYS>>\n\n' }}{% elif message['role'] == 'user' %}{{ '[INST] ' }}{# Render all images first #}{% for content in message['content'] | selectattr('type', 'equalto', 'image') %}{{ '<image>\n' }}{% endfor %}{# Render all text next #}{% for content in message['content'] | selectattr('type', 'equalto', 'text') %}{{ content['text'] }}{% endfor %}{{' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'][0]['text'] + '<\\s> '}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
+}

config.json

@@ -0,0 +1,68 @@
+{
+  "_name_or_path": "/home/ea/work/my_optimum_intel/optimum-intel/tiny-random-llava-next/config.json",
+  "architectures": [
+    "LlavaNextForConditionalGeneration"
+  ],
+  "ignore_index": -100,
+  "image_grid_pinpoints": [
+    [
+      30,
+      60
+    ],
+    [
+      60,
+      30
+    ],
+    [
+      60,
+      60
+    ],
+    [
+      90,
+      30
+    ],
+    [
+      30,
+      90
+    ]
+  ],
+  "image_token_index": 32000,
+  "model_type": "llava_next",
+  "projector_hidden_act": "gelu",
+  "text_config": {
+    "_name_or_path": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "hidden_size": 16,
+    "intermediate_size": 64,
+    "model_type": "llama",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 4,
+    "pad_token_id": 3201,
+    "torch_dtype": "float32",
+    "vocab_size": 32002
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_image_newline_parameter": true,
+  "vision_config": {
+    "attention_dropout": 0.1,
+    "dropout": 0.1,
+    "hidden_size": 32,
+    "image_size": 30,
+    "intermediate_size": 37,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "patch_size": 2,
+    "projection_dim": 32
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32002
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 1,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66020b265c84677d19fc68afc67669f9ff1efce2e8cd8baeea21f520510d2477
+size 4225912

preprocessor_config.json

@@ -0,0 +1,51 @@
+{
+  "aspect_ratio_setting": "anyres",
+  "crop_size": {
+    "height": 30,
+    "width": 30
+  },
+  "image_grid_pinpoints": [
+    [
+      30,
+      60
+    ],
+    [
+      60,
+      30
+    ],
+    [
+      60,
+      60
+    ],
+    [
+      90,
+      30
+    ],
+    [
+      30,
+      90
+    ]
+  ],
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "LlavaNextImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "LlavaNextProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 30
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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 +1,57 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "processor_class": "LlavaProcessor",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}