Upload LlavaForConditionalGeneration

config.json

@@ -2,29 +2,46 @@
   "architectures": [
     "LlavaForConditionalGeneration"
   ],
-  "ignore_index": -100,
   "image_seq_length": 576,
   "image_token_index": 32000,
   "model_type": "llava",
+  "multimodal_projector_bias": true,
   "projector_hidden_act": "gelu",
   "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
     "head_dim": 2,
+    "hidden_act": "silu",
     "hidden_size": 8,
+    "initializer_range": 0.02,
     "intermediate_size": 32,
+    "max_position_embeddings": 2048,
+    "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,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "use_cache": true,
     "vocab_size": 32005
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.47.0.dev0",
+  "transformers_version": "4.54.0.dev0",
   "vision_config": {
-    "hidden_size": 8,
+    "attention_dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 16,
     "image_size": 336,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
     "intermediate_size": 32,
+    "layer_norm_eps": 1e-05,
     "model_type": "clip_vision_model",
     "num_attention_heads": 4,
+    "num_channels": 3,
     "num_hidden_layers": 2,
     "patch_size": 14,
     "projection_dim": 8

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.47.0.dev0"
+  "transformers_version": "4.54.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb60b1bc3c41b94aec9c4c24111b3dd3a5b1853317fce7d967cbea4263464e1a
-size 2108896
+oid sha256:5f54b0ec090dd9d4ec1955951dc2d1449bcf1cffebcee2f651554858609f23c6
+size 2157456