Upload Qwen2.5-32B-Instruct-v8-k256-256-woft model

.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

generation_config.json

@@ -1,25 +1,6 @@
 {
-  "attn_implementation": "flash_attention_2",
+  "_from_model_config": true,
   "bos_token_id": 151643,
-  "cache_config": null,
-  "cache_implementation": null,
-  "do_sample": true,
-  "dola_layers": null,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "max_matching_ngram_size": null,
-  "min_p": null,
-  "output_logits": null,
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.05,
-  "return_legacy_cache": true,
-  "stop_strings": null,
-  "temperature": 0.7,
-  "token_healing": false,
-  "top_k": 20,
-  "top_p": 0.8,
-  "transformers_version": "4.37.2",
-  "watermarking_config": null
+  "eos_token_id": 151645,
+  "transformers_version": "4.49.0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f10244af3b0b6bbf3e589052cffd060efff437744f8d1259d0b1d2a6be5565d
-size 4998724280
+oid sha256:ddc785417c3ec79f2a602689038f8898a26c2cf7892ec11d6a4935cb9de5feeb
+size 4995382720

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335035ae090dde55544156f71ece74da277b8c21437488b717d1e7b91567eaae
-size 4388492824
+oid sha256:1eb9b2b1ad97027e422105edc5c6bab6e49d91052062e5a391ff04347fb8cdea
+size 4384314712

tokenizer_config.json

@@ -199,6 +199,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "errors": "replace",
+  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",