Upload folder using huggingface_hub

.ipynb_checkpoints/quantize_config-checkpoint.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": true,
+  "quant_method": "gptq"
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/data/unsloth/final/Llama-3-Alpha-ORPO-gpt4o-v1",
+  "_name_or_path": "allganize/Llama-3-Alpha-Ko-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -20,10 +21,10 @@
   "pretraining_tp": 1,
   "quantization_config": {
     "bits": 4,
-    "checkpoint_format": "marlin",
     "damp_percent": 0.01,
     "desc_act": false,
     "group_size": 128,
+    "is_marlin_format": true,
     "model_file_base_name": null,
     "model_name_or_path": null,
     "quant_method": "gptq",
@@ -36,7 +37,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.40.0",
+  "transformers_version": "4.41.0",
   "unsloth_version": "2024.5",
   "use_cache": true,
   "vocab_size": 128256

gptq_model-4bit-128g.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7499a142bdd73bf148d9668a576714f17ae9c06fe8679776a33fe009de470350
-size 5700648184
+oid sha256:e467556a53e8e6781e59d02734976ccebb8961b8040f911fa9d746e9749422ee
+size 5735720552

quantize_config.json

@@ -8,7 +8,6 @@
   "true_sequential": true,
   "model_name_or_path": null,
   "model_file_base_name": null,
-  "quant_method": "gptq",
-  "checkpoint_format": "marlin",
-  "is_marlin_format": true
+  "is_marlin_format": true,
+  "quant_method": "gptq"
 }