Upload LlavaForConditionalGeneration

config.json

@@ -2,12 +2,10 @@
   "architectures": [
     "LlavaForConditionalGeneration"
   ],
-  "dtype": "bfloat16",
   "ignore_index": -100,
-  "image_seq_length": 576,
+  "image_token_id": 32000,
   "image_token_index": 32000,
   "model_type": "llava",
-  "multimodal_projector_bias": true,
   "pad_token_id": 32001,
   "projector_hidden_act": "gelu",
   "text_config": {
@@ -15,42 +13,21 @@
     "architectures": [
       "LlamaForCausalLM"
     ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "dtype": "bfloat16",
-    "head_dim": 128,
-    "hidden_act": "silu",
-    "hidden_size": 4096,
-    "initializer_range": 0.02,
-    "intermediate_size": 11008,
     "max_position_embeddings": 4096,
-    "mlp_bias": false,
     "model_type": "llama",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 32,
-    "num_key_value_heads": 32,
-    "pretraining_tp": 1,
+    "pad_token_id": 0,
     "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
-    "rope_theta": 10000.0,
-    "use_cache": true,
+    "torch_dtype": "float16",
     "vocab_size": 32064
   },
-  "tie_word_embeddings": false,
-  "transformers_version": "4.57.3",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
   "vision_config": {
-    "attention_dropout": 0.0,
-    "dtype": "bfloat16",
-    "hidden_act": "quick_gelu",
     "hidden_size": 1024,
     "image_size": 336,
-    "initializer_factor": 1.0,
-    "initializer_range": 0.02,
     "intermediate_size": 4096,
-    "layer_norm_eps": 1e-05,
     "model_type": "clip_vision_model",
     "num_attention_heads": 16,
-    "num_channels": 3,
     "num_hidden_layers": 24,
     "patch_size": 14,
     "projection_dim": 768,

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 32001,
-  "transformers_version": "4.57.3"
+  "transformers_version": "4.37.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ccf90d19db39ec3c090bdfbb88ce3fc5059127df19b60910a279e997735b54
+oid sha256:d40376e663a1eef76f793aca6c9d95c7291041fdf2c606bae89f153a96d6030b
 size 4992930688

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6564cb8de7f87fc34de07b4c80ca9600bd0bd2d6adb38fc8352865a207fb8bb7
+oid sha256:584f24b6e2c44106752c81cf55ca2ca9fc213a2aab86ae0c2bfcc1cea69e17b5
 size 4957878552

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1542e7b965304c750e9a56efc57e94ea4b6843338283b25a06252d356f64e32f
+oid sha256:f9ec85793f6bb0b7e065072a075ddc018850db9b059caef1bba5b93373cfd069
 size 4176137496

model.safetensors.index.json

@@ -1,6 +1,5 @@
 {
   "metadata": {
-    "total_parameters": 7063427072,
     "total_size": 14126854144
   },
   "weight_map": {