Upload LlamaForCausalLM

config.json

@@ -1,28 +1,40 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
   "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": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
+  "rope_scaling": {
+    "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": "float16",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.48.0.dev0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -3,10 +3,10 @@
   "do_sample": true,
   "eos_token_id": [
     128001,
+    128008,
     128009
   ],
-  "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.48.0.dev0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6c16b86bc94e4edd78884ff3bfb41c90eab6c681a3507a5875ed2dbbf55ef7
+oid sha256:aeba141da2d9c3cc32feacba9ab93238674498535e86e924396630553902bcf5
 size 4976698592

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2252fd0c716841fe555386a5cf95c075294a493c6e9673694345e4f567e2b8
+oid sha256:7c29143afed5b3fa41c4066a6e20eb96ad8540effb2841feef4440e085d38e6d
 size 4999802616

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05b0e0714d676b388dd1634ed442878ab5b99a0f378ce411505276c3275737a
+oid sha256:6da28fb8e18d5c208fe59585748cbfc995188c7ec98271becb9977ac2427fd3c
 size 4915916080

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04db72068fd46f4770156e74f503bcdf4fdabb519a6391bb46b871218fb6ca4
+oid sha256:013bc9e3d5d06232d8a358ad3cd323b732255d31e2debe3bf0c6325b88110ae0
 size 1168138808