Upload 8 files

adapter_config.json

@@ -0,0 +1,20 @@
+{
+  "base_model_name_or_path": null,
+  "bias": "none",
+  "enable_lora": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "merge_weights": false,
+  "modules_to_save": [
+    "image_projection_layer",
+    "embed_tokens",
+    "lm_head",
+    "visual_resampler"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "target_modules": ".*(vision_model|text_model).*(self_attn|mlp).*(q_proj|k_proj|v_proj|o_proj|out_proj|fc1|fc2|gate_proj|down_proj|up_proj)$",
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c70c9fdc2f462a138b6739ae963bc1cd16515363363307927ff0eda16e7176d
+size 1027494823

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "</img>": 49955,
+  "<img>": 49954,
+  "<img_token>": 49957,
+  "<pad>": 49956
+}

config.json

@@ -0,0 +1,107 @@
+{
+    "vision_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": 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,
+      "dropout": 0.0,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "quick_gelu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 224,
+      "initializer_factor": 1.0,
+      "initializer_range": 0.02,
+      "intermediate_size": 4096,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-05,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "clip_vision_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 24,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "projection_dim" : 768,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "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": "4.16.0.dev0",
+      "use_bfloat16": false
+    },
+    "text_config": {
+      "architectures": [
+        "LlamaForCausalLM"
+      ],
+      "bos_token_id": 1,
+      "eos_token_id": 2,
+      "hidden_act": "silu",
+      "hidden_size": 4096,
+      "initializer_range": 0.02,
+      "intermediate_size": 11008,
+      "max_position_embeddings": 2048,
+      "model_type": "llama",
+      "num_attention_heads": 32,
+      "num_hidden_layers": 32,
+      "pad_token_id": 0,
+      "rms_norm_eps": 1e-06,
+      "tie_word_embeddings": false,
+      "torch_dtype": "float16",
+      "transformers_version": "4.30.1",
+      "use_cache": true,
+      "vocab_size": 49958
+    },
+    "image_size": 224,
+    "use_visual_resampler": true,
+    "visual_resampler_config": {
+      "num_query_tokens": 64,
+      "num_hidden_layers": 6,
+      "hidden_size": 1024,
+      "num_attention_heads": 16,
+      "intermediate_size": 4096
+    },
+    "tie_word_embeddings": false,
+    "vocab_size": 49958
+}

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": [
+    "<img>",
+    "</img>",
+    "<pad>",
+    "<img_token>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d967e855b1213a439df6c8ce2791f869c84b4f3b6cfacf22b86440b8192a2f8
+size 757972

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "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": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}