SKIML-ICL/Llama-3-8B-Inst_qa_squad-ans-v2_ckp-1500-3000

.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

@@ -48,7 +48,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.44.1
+- Transformers 4.45.1
 - Pytorch 2.4.0
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.20.0

config.json

@@ -24,7 +24,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.44.1",
+  "transformers_version": "4.45.1",
   "use_cache": false,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.44.1"
+  "transformers_version": "4.45.1"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea690b172138e5cd78b7d7d0deac0850d543786b6ebb08e1c1ee051bb698129
+oid sha256:912563dad4cfa4ebeb03eaacb057c0f4e0de52f942cbfd51326f1c633c89846a
 size 5496