Upload folder using huggingface_hub

config.json

@@ -2,22 +2,21 @@
   "architectures": [
     "LlavaForConditionalGeneration"
   ],
+  "dtype": "bfloat16",
   "image_seq_length": 729,
   "image_token_index": 128077,
   "model_type": "llava",
   "multimodal_projector_bias": true,
   "projector_hidden_act": "gelu",
   "quantization_config": {
-    "autoround_version": "0.5.1",
+    "autoround_version": "0.7.0",
     "bits": 4,
     "block_name_to_quantize": "model.language_model.layers",
-    "damp_percent": 0.01,
     "data_type": "int",
-    "desc_act": false,
     "group_size": 128,
-    "quant_method": "gptq",
-    "sym": true,
-    "true_sequential": false
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "sym": true
   },
   "text_config": {
     "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
@@ -27,6 +26,7 @@
     "attention_bias": false,
     "attention_dropout": 0.0,
     "bos_token_id": 128000,
+    "dtype": "bfloat16",
     "eos_token_id": [
       128001,
       128008,
@@ -53,18 +53,17 @@
       "rope_type": "llama3"
     },
     "rope_theta": 500000.0,
-    "torch_dtype": "bfloat16",
     "use_cache": true,
     "vocab_size": 128256
   },
-  "torch_dtype": "float16",
-  "transformers_version": "4.52.3",
+  "transformers_version": "4.56.1",
   "vision_config": {
     "_name_or_path": "google/siglip2-so400m-patch14-384",
     "architectures": [
       "SiglipVisionModel"
     ],
     "attention_dropout": 0.0,
+    "dtype": "bfloat16",
     "hidden_act": "gelu_pytorch_tanh",
     "hidden_size": 1152,
     "image_size": 384,
@@ -74,8 +73,7 @@
     "num_attention_heads": 16,
     "num_channels": 3,
     "num_hidden_layers": 27,
-    "patch_size": 14,
-    "torch_dtype": "bfloat16"
+    "patch_size": 14
   },
   "vision_feature_layer": -2,
   "vision_feature_select_strategy": "full"

generation_config.json

@@ -1,10 +1,13 @@
 {
   "_from_model_config": true,
   "bos_token_id": 128000,
+  "do_sample": true,
   "eos_token_id": [
     128001,
     128008,
     128009
   ],
-  "transformers_version": "4.52.3"
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.56.1"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057d260b474b0e784d4f2e6dde2816fdeff3431fdefa94ea98d3a3ea65bc17a9
-size 4983780528
+oid sha256:9a615187113e076dfb191e1a97258839889cadfbce156870fe2b205fb35f6519
+size 4979609960

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9b5820b0e324f31de5eadd26cbf980448f3648df296e8e177686c7e72f3a413
-size 1648700952
+oid sha256:8a8269df045da542a05551d467df4468d5df13d3738f89a93e40647d68954a40
+size 1647861000

quantization_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "autoround_version": "0.7.0",
+  "block_name_to_quantize": "model.language_model.layers",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq"
+}

tokenizer_config.json

@@ -2059,5 +2059,5 @@
   ],
   "model_max_length": 131072,
   "processor_class": "LlavaProcessor",
-  "tokenizer_class": "PreTrainedTokenizer"
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }