Upload folder using huggingface_hub

config.json

@@ -17,28 +17,17 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
-    "batch_size": 1,
     "bits": 4,
-    "block_name_to_quantize": null,
-    "cache_block_outputs": true,
+    "checkpoint_format": "gptq",
     "damp_percent": 0.01,
-    "dataset": null,
     "desc_act": true,
-    "exllama_config": {
-      "version": 1
-    },
     "group_size": 128,
-    "max_input_length": null,
-    "model_seqlen": null,
-    "module_name_preceding_first_block": null,
-    "modules_in_block_to_quantize": null,
-    "pad_token_id": null,
+    "model_file_base_name": null,
+    "model_name_or_path": null,
     "quant_method": "gptq",
+    "static_groups": false,
     "sym": true,
-    "tokenizer": null,
-    "true_sequential": true,
-    "use_cuda_fp16": false,
-    "use_exllama": true
+    "true_sequential": true
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901c88e4b3b27c2054b4ab0cbc2ba8d57462c70916f364457e617f136a80f326
+oid sha256:7ef5bb24009e13201e153c2cc21b6e9bf1288336d2ea1232c4b4c0814e4f7b6f
 size 4685047152