Upload model Meta-Llama-3.1-8B-Instruct-v8-k65536-65536-woft

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,7 +1,7 @@
+
 ---
 license: llama3.1
 ---
-
 **Disclaimer**: 
 
 The model is reproduced based on the paper *VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models* [github](https://github.com/microsoft/vptq) and [arXiv](https://arxiv.org/abs/2409.17066)
@@ -18,14 +18,14 @@ The PPL test results are for reference only and were collected using GPTQ testin
 
 ```json
 {
-  "ctx_2048": {
-    "wikitext2": 7.414072513580322
-  },
-  "ctx_4096": {
-    "wikitext2": 6.940601348876953
-  },
-  "ctx_8192": {
-    "wikitext2": 6.678436756134033
-  }
+    "ctx_2048": {
+        "wikitext2": 7.414072513580322
+    },
+    "ctx_4096": {
+        "wikitext2": 6.940601348876953
+    },
+    "ctx_8192": {
+        "wikitext2": 6.678436756134033
+    }
 }
-```
+```

config.json

@@ -5411,7 +5411,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.45.1",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -7,7 +7,10 @@
     128008,
     128009
   ],
+  "num_assistant_tokens": 5,
+  "num_assistant_tokens_schedule": "heuristic",
+  "return_legacy_cache": true,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.44.2"
+  "transformers_version": "4.45.1"
 }