llm-jp
/

llm-jp-3-8x1.8b-instruct2

Text Generation

text-generation-inference

Model card Files Files and versions Community

Taka008 commited on Mar 31

Commit

aa827b3

·

verified ·

1 Parent(s): 2216185

Upload config.json

Files changed (1) hide show

config.json +2 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "llm-jp/llm-jp-3-8x1.8b-instruct2",
   "architectures": [
     "MixtralForCausalLM"
   ],
@@ -27,7 +27,7 @@
   "router_jitter_noise": 0.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 99584

 {
+  "_name_or_path": "/home/shared/experiments/0117_moe-tuning/checkpoints/nemo-to-hf/sft-c8J2tAw3pU",
   "architectures": [
     "MixtralForCausalLM"
   ],
   "router_jitter_noise": 0.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.47.0",
   "use_cache": true,
   "vocab_size": 99584