gradientai
/

Llama-3-8B-Instruct-Gradient-1048k

Text Generation

text-generation-inference

Model card Files Files and versions

michaelfeil commited on May 4, 2024

Commit

23fdb98

·

verified ·

1 Parent(s): 46e7c2f

Update config.json

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gradientai/llama3-run1-stage524k-fm-v3",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -19,10 +19,10 @@
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 2804339835.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.1",
   "use_cache": true,
   "vocab_size": 128256
 }

 {
+  "_name_or_path": "gradientai/llama3-8b-stage262k-chat",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
+  "rope_theta": 3580165449.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0.dev0",
   "use_cache": true,
   "vocab_size": 128256
 }