Upload LlamaForCausalLM

config.json

@@ -1,17 +1,17 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
   "hidden_act": "silu",
   "hidden_size": 128,
   "initializer_range": 0.02,
   "intermediate_size": 384,
-  "max_position_embeddings": 4096,
+  "max_position_embeddings": 8192,
   "model_type": "llama",
   "num_attention_heads": 8,
   "num_hidden_layers": 2,
@@ -19,10 +19,10 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.38.1",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 10000
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
   "transformers_version": "4.38.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2aee7807c71ae3a7e9ce0fce8b8ff2af168d8970ebdd4c36ec44ef07301c3a
-size 34345688
+oid sha256:3353ddaf77c731ae0114284de26c0639c8b89b305af9087c364fcd980c2f1c21
+size 11817680