Upload LlavaForConditionalGeneration

config.json

@@ -2,33 +2,41 @@
   "architectures": [
     "LlavaForConditionalGeneration"
   ],
+  "ignore_index": -100,
   "image_seq_length": 576,
   "image_token_index": 32000,
   "model_type": "llava",
   "multimodal_projector_bias": true,
+  "pad_token_id": 32001,
   "projector_hidden_act": "gelu",
   "text_config": {
+    "_name_or_path": "lmsys/vicuna-7b-v1.5",
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
     "attention_bias": false,
     "attention_dropout": 0.0,
-    "head_dim": 4,
+    "head_dim": 128,
     "hidden_act": "silu",
     "hidden_size": 16,
     "initializer_range": 0.02,
-    "intermediate_size": 32,
-    "max_position_embeddings": 2048,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 4096,
     "mlp_bias": false,
     "model_type": "llama",
     "num_attention_heads": 4,
     "num_hidden_layers": 2,
     "num_key_value_heads": 2,
     "pretraining_tp": 1,
-    "rms_norm_eps": 1e-06,
+    "rms_norm_eps": 1e-05,
     "rope_scaling": null,
     "rope_theta": 10000.0,
+    "torch_dtype": "float16",
     "use_cache": true,
-    "vocab_size": 32005
+    "vocab_size": 32064
   },
-  "torch_dtype": "float32",
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.56.0.dev0",
   "vision_config": {
     "attention_dropout": 0.0,
@@ -37,15 +45,18 @@
     "image_size": 336,
     "initializer_factor": 1.0,
     "initializer_range": 0.02,
-    "intermediate_size": 32,
+    "intermediate_size": 4096,
     "layer_norm_eps": 1e-05,
     "model_type": "clip_vision_model",
     "num_attention_heads": 4,
     "num_channels": 3,
     "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
     "patch_size": 14,
-    "projection_dim": 8
+    "projection_dim": 768,
+    "vocab_size": 32000
   },
   "vision_feature_layer": -2,
-  "vision_feature_select_strategy": "default"
+  "vision_feature_select_strategy": "default",
+  "vocab_size": 32064
 }

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "pad_token_id": 32001,
   "transformers_version": "4.56.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97667e386c55a9029f3d4dad52c8c7a4b14ac4b1bcd3defb4d62c05a3af7a241
-size 4218064
+oid sha256:a32ec14543807116ef58a58004b5c2991650262e60958dbe95019f4b92d35ebf
+size 4855896