Trained with Unsloth

config.json

@@ -1,36 +1,42 @@
 {
-  "_name_or_path": "unsloth/llama-3-8b-Instruct-bnb-4bit",
+  "_name_or_path": "unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128009,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 10000,
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 128255,
+  "pad_token_id": 128004,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
-    "factor": 1.220703125,
-    "rope_type": "linear",
-    "type": "linear"
+    "factor": 8.0,
+    "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": "4.47.1",
-  "unsloth_version": "2024.12.12",
+  "unsloth_version": "2025.1.5",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -3,10 +3,11 @@
   "do_sample": true,
   "eos_token_id": [
     128001,
+    128008,
     128009
   ],
-  "max_length": 10000,
-  "pad_token_id": 128255,
+  "max_length": 131072,
+  "pad_token_id": 128004,
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "4.47.1"

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ac339b37d8f33aafca169093fdacdb0296c738914bcd9850fbd37c1c1bad2b
+oid sha256:56cef4a191d853b71ceec0e01b85738d9421a2d48d7b38793c419c431231b2e8
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eefc52155d4af5b33fc10cd94966c6edeb9edb99f37d84ec723f71ec375ba2eb
+oid sha256:9ad771eb8c3cebc35f72e6f26db3dd0a3a8bb01f7764de136963182c3857ad7a
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5c563dd1e8886e0f779fb851b13dd6704b892f7c4182e2372c490c4590b1c7b
+oid sha256:8afe1b1680b1384dbf3c91ac5f08f28d47cf8c125966701dd040ad4558d313ab
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0260de6ef20c12be76e87c45ee3005b644547c613992065e62c6e31fa2d140
+oid sha256:299045cd1b7244d4b28041f9a08b375223f5a903aa6f585a1957e3dde2b4008b
 size 1168138808