9f7215ccd7cb4c185eb4fac86e4d56da03631027e58e2bf4ed1b9ebafab18c8e

config.json

@@ -9,7 +9,7 @@
   "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
-  "image_aspect_ratio": "pad",
+  "image_aspect_ratio": "resize",
   "image_crop_resolution": null,
   "image_grid_pinpoints": null,
   "image_split_resolution": null,
@@ -28,7 +28,7 @@
   "mm_vision_select_layer": -2,
   "mm_vision_tower": "openai/clip-vit-large-patch14-336",
   "mm_vision_tower_lr": 2e-06,
-  "model_type": "llama",
+  "model_type": "llava_llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
@@ -41,9 +41,10 @@
   "tokenizer_model_max_length": 4096,
   "tokenizer_padding_side": "right",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "transformers_version": "4.40.0.dev0",
   "use_cache": true,
   "use_mm_proj": true,
   "vision_tower_pretrained": null,
-  "vocab_size": 32000
+  "vocab_size": 32000,
+  "s2": true
 }

generation_config.json

@@ -1,9 +1,10 @@
 {
+  "attn_implementation": "flash_attention_2",
   "bos_token_id": 1,
   "eos_token_id": 2,
   "max_length": 4096,
   "pad_token_id": 0,
   "temperature": 0.9,
   "top_p": 0.6,
-  "transformers_version": "4.39.3"
+  "transformers_version": "4.40.0.dev0"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:990622a241c232a2aef2e03d149378b3536e6dbc29695b194293b69810dad045
-size 7160
+oid sha256:5c98a00b5dd88431b27304126692f44fcac408310ecc11cea928cd126156b36f
+size 7544