haoranli-ml
/

Llama-3-8B-HardClip-64k-Base

Model card Files Files and versions

haoranli-ml commited on Jan 31

Commit

2a7a649

·

verified ·

1 Parent(s): 32235d0

Update config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "checkpoints/lcft_Meta-Llama-3-8B_long-context-65536_ProLong64KMix_bsz256_steps1250_lr1e-5_warmup0.1/checkpoint-1250",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -11,7 +11,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,

 {
+  "_name_or_path": "haoranli-ml/Llama-3-8B-HardClip-64k-Base",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
+  "max_position_embeddings": 65536,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,