first commit

config.json

@@ -0,0 +1,148 @@
+{
+  "_name_or_path": "jiajunlong/TinyLLaVA-OpenELM-450M-CLIP-0.55B",
+  "architectures": [
+    "TinyLlavaForConditionalGeneration"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration.TinyLlavaConfig",
+    "AutoModelForCausalLM": "modeling_tinyllava_elm.TinyLlavaForConditionalGeneration"
+  },
+  "cache_dir": null,
+  "connector_type": "mlp2x_gelu",
+  "hidden_size": 1536,
+  "ignore_index": -100,
+  "image_aspect_ratio": "square",
+  "image_token_index": -200,
+  "llm_model_name_or_path": "apple/OpenELM-450M-Instruct",
+  "model_type": "tinyllava",
+  "num_queries": 128,
+  "num_resampler_layers": 3,
+  "pad_token": "<unk>",
+  "resampler_hidden_size": 768,
+  "text_config": {
+    "_name_or_path": "apple/OpenELM-450M-Instruct",
+    "activation_fn_name": "swish",
+    "architectures": [
+      "OpenELMForCausalLM"
+    ],
+    "auto_map": {
+      "AutoConfig": "apple/OpenELM-450M-Instruct--configuration_openelm.OpenELMConfig",
+      "AutoModelForCausalLM": "apple/OpenELM-450M-Instruct--modeling_openelm.OpenELMForCausalLM"
+    },
+    "ffn_dim_divisor": 256,
+    "ffn_multipliers": [
+      0.5,
+      0.68,
+      0.87,
+      1.05,
+      1.24,
+      1.42,
+      1.61,
+      1.79,
+      1.97,
+      2.16,
+      2.34,
+      2.53,
+      2.71,
+      2.89,
+      3.08,
+      3.26,
+      3.45,
+      3.63,
+      3.82,
+      4.0
+    ],
+    "ffn_with_glu": true,
+    "head_dim": 64,
+    "max_context_length": 2048,
+    "model_dim": 1536,
+    "model_type": "openelm",
+    "normalization_layer_name": "rms_norm",
+    "normalize_qk_projections": true,
+    "num_gqa_groups": 4,
+    "num_kv_heads": [
+      3,
+      3,
+      3,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      4,
+      5,
+      5,
+      5,
+      5,
+      5,
+      5,
+      6,
+      6,
+      6,
+      6
+    ],
+    "num_query_heads": [
+      12,
+      12,
+      12,
+      16,
+      16,
+      16,
+      16,
+      16,
+      16,
+      16,
+      20,
+      20,
+      20,
+      20,
+      20,
+      20,
+      24,
+      24,
+      24,
+      24
+    ],
+    "num_transformer_layers": 20,
+    "qkv_multipliers": [
+      0.5,
+      1.0
+    ],
+    "rope_freq_constant": 10000,
+    "rope_max_length": 4096,
+    "share_input_output_layers": true,
+    "tie_word_embeddings": true,
+    "torch_dtype": "float16"
+  },
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "tokenizer_padding_side": "right",
+  "tokenizer_use_fast": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.3",
+  "tune_type_connector": "full",
+  "tune_type_llm": "lora",
+  "tune_type_vision_tower": "lora",
+  "tune_vision_tower_from_layer": 0,
+  "use_cache": true,
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "image_size": 224,
+    "intermediate_size": 3072,
+    "model_name_or_path": "openai/clip-vit-base-patch16",
+    "model_name_or_path2": "",
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "patch_size": 16,
+    "projection_dim": 512
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "patch",
+  "vision_hidden_size": 768,
+  "vision_model_name_or_path": "openai/clip-vit-base-patch16",
+  "vision_model_name_or_path2": "",
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4530afbf359f52d8ada0b087f1c67e94cd1a52a2f0aa5dbba50f3d22f60fa19
+size 1093091592

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<unk>",
+  "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 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}