v1.0.6-reupload

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/mkurman/gitlab/ai/model-trainer/mergekit/results/llama_2_4b/6400_snl_mrf_base_3_deduplicated_8b_3",
+  "_name_or_path": "../results/llama-2_4b/2024-10-19 20_40_03/checkpoint-6600",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -37,7 +37,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
-  "unsloth_version": "2024.9.post3",
+  "unsloth_version": "2024.10.2",
   "use_cache": true,
   "vocab_size": 128262
 }

generation_config.json

@@ -1,11 +1,14 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 128000,
+  "do_sample": true,
   "eos_token_id": [
     128001,
     128008,
     128009
   ],
+  "max_length": 131072,
   "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.45.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d033f6d426155f0bce4e8194352139e4b81ae39fd2968f177633bd97ae8aa58
-size 4943287208
+oid sha256:e5fd9365880a8abf926ebeb44f3ee25ce80244ded2d61cbe1760f2fb58991054
+size 4943336360