Upload folder using huggingface_hub

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "_name_or_path": "../../submission/models/llava-v1.6-mistral-7b",
   "architectures": [
-    "LlavaLlamaForCausalLM"
+    "LlavaMistralForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,
@@ -49,10 +49,23 @@
   "mm_vision_select_layer": -2,
   "mm_vision_tower": "openai/clip-vit-large-patch14-336",
   "mm_vision_tower_lr": 2e-06,
-  "model_type": "llava",
+  "model_type": "llava_mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "quantization_config": {
+    "bits": 4,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "group_size": 128,
+    "is_marlin_format": false,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
+    "quant_method": "gptq",
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true
+  },
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "sliding_window": null,
@@ -60,22 +73,11 @@
   "tokenizer_model_max_length": 4096,
   "tokenizer_padding_side": "left",
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.38.1",
   "tune_mm_mlp_adapter": false,
   "tune_mm_vision_resampler": false,
   "unfreeze_mm_vision_tower": true,
   "use_cache": true,
   "use_mm_proj": true,
-  "vocab_size": 32000,
-  "quantization_config": {
-    "bits": 4,
-    "group_size": 128,
-    "damp_percent": 0.1,
-    "desc_act": true,
-    "sym": true,
-    "true_sequential": true,
-    "model_name_or_path": null,
-    "model_file_base_name": "model",
-    "quant_method": "gptq"
-  }
+  "vocab_size": 32000
 }

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116d3c4ba4388fbdd027f13f83d060d39cc6e008930caf9c3037d5a5071c3d14
+size 5981509688

quantize_config.json

@@ -0,0 +1,13 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null,
+  "is_marlin_format": false,
+  "quant_method": "gptq"
+}