Upload model

config.json

@@ -0,0 +1,131 @@
+{
+  "_name_or_path": "ybelkada/llava-1.5-7b",
+  "additional_vocab_size": 0,
+  "alpha_initializer": "zeros",
+  "alpha_type": "float",
+  "alphas_initializer_range": 0.0,
+  "architectures": [
+    "CLIPVisionModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "cross_layer_interval": 1,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "freeze_lm_head": false,
+  "freeze_text_layers": true,
+  "freeze_text_module_exceptions": [],
+  "freeze_vision_layers": true,
+  "freeze_vision_module_exceptions": [],
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "ignore_index": -100,
+  "image_size": 336,
+  "image_token_index": -200,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "model_type": "clip_vision_model",
+  "num_attention_heads": 32,
+  "num_channels": 3,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "patch_size": 14,
+  "projection_dim": 512,
+  "projector_hidden_act": "gelu",
+  "qk_layer_norms": false,
+  "rms_norm_eps": 1e-06,
+  "text_config": {
+    "_name_or_path": "meta-llama/Llama-2-7b-hf",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "use_cache": true,
+  "use_resampler": false,
+  "vision_config": {
+    "model_type": "llava"
+  },
+  "vision_feature_layer": -2,
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0eefa6f9ab14c0062f65bf6ce4d4db90b844d7fd9b0bd9b1eae6b419797eeb
+size 1214077616