Upload folder using huggingface_hub

config.json

@@ -18,45 +18,21 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "quantization_config": {
-    "backend": "auto",
-    "batch_size": 1,
     "bits": 4,
-    "block_name_to_quantize": null,
-    "cache_block_outputs": true,
-    "checkpoint_format": "gptq_v2",
-    "damp_percent": 0.01,
-    "dataset": null,
-    "desc_act": true,
-    "exllama_config": {
-      "version": 1
-    },
-    "group_size": 128,
-    "max_input_length": null,
-    "meta": {
-      "quantizer": [
-        "optimum:1.25.3",
-        "gptqmodel:2.2.0"
-      ]
-    },
-    "model_seqlen": null,
-    "module_name_preceding_first_block": null,
-    "modules_in_block_to_quantize": null,
-    "pad_token_id": null,
-    "quant_method": "gptq",
-    "sym": true,
-    "tokenizer": null,
-    "true_sequential": true,
-    "use_cuda_fp16": false,
-    "use_exllama": true
+    "group_size": 64,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
   },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "sliding_window": null,
   "tie_word_embeddings": true,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.52.4",
-  "use_cache": true,
+  "use_cache": false,
   "use_sliding_window": false,
   "vocab_size": 151936
 }

generation_config.json

@@ -1,5 +1,6 @@
 {
   "bos_token_id": 151643,
+  "do_sample": true,
   "eos_token_id": 151643,
   "max_new_tokens": 2048,
   "transformers_version": "4.52.4"

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4aecc6bd06887003dceb2208ba41ad2c3c3ec82088f5dac7fef9e9e3cb7b21bc
-size 541343728
+oid sha256:59df2db82b7752e44456f214a860ece524fa741dbb85d03c362051058fc453c4
+size 860074360