Upload folder using huggingface_hub

config.json

@@ -1,10 +1,51 @@
 {
+  "_name_or_path": "/home/meta-llama/Meta-Llama-3.1-405B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
+  "compression_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": {
+          "block_structure": null,
+          "dynamic": true,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "memoryless",
+          "observer_kwargs": {},
+          "strategy": "token",
+          "symmetric": true,
+          "type": "float"
+        },
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "channel",
+          "symmetric": true,
+          "type": "float"
+        }
+      }
+    },
+    "format": "naive-quantized",
+    "global_compression_ratio": 1.240844659615461,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "frozen"
+  },
   "eos_token_id": [
     128001,
     128008,
@@ -24,15 +65,15 @@
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
-    "low_freq_factor": 1.0,
     "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
     "original_max_position_embeddings": 8192,
     "rope_type": "llama3"
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.3",
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.1",
   "use_cache": true,
   "vocab_size": 128256
-}
+}

generation_config.json

@@ -1,12 +1,10 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 128000,
-  "do_sample": true,
   "eos_token_id": [
     128001,
     128008,
     128009
   ],
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.42.3"
-}
+  "transformers_version": "4.43.1"
+}

tokenizer.json

@@ -2329,69 +2329,10 @@
     ]
   },
   "post_processor": {
-    "type": "Sequence",
-    "processors": [
-      {
-        "type": "ByteLevel",
-        "add_prefix_space": true,
-        "trim_offsets": false,
-        "use_regex": true
-      },
-      {
-        "type": "TemplateProcessing",
-        "single": [
-          {
-            "SpecialToken": {
-              "id": "<|begin_of_text|>",
-              "type_id": 0
-            }
-          },
-          {
-            "Sequence": {
-              "id": "A",
-              "type_id": 0
-            }
-          }
-        ],
-        "pair": [
-          {
-            "SpecialToken": {
-              "id": "<|begin_of_text|>",
-              "type_id": 0
-            }
-          },
-          {
-            "Sequence": {
-              "id": "A",
-              "type_id": 0
-            }
-          },
-          {
-            "SpecialToken": {
-              "id": "<|begin_of_text|>",
-              "type_id": 1
-            }
-          },
-          {
-            "Sequence": {
-              "id": "B",
-              "type_id": 1
-            }
-          }
-        ],
-        "special_tokens": {
-          "<|begin_of_text|>": {
-            "id": "<|begin_of_text|>",
-            "ids": [
-              128000
-            ],
-            "tokens": [
-              "<|begin_of_text|>"
-            ]
-          }
-        }
-      }
-    ]
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": false,
+    "use_regex": true
   },
   "decoder": {
     "type": "ByteLevel",