HachiML
/

Bit-Llama2-jp-123M-test-1

Text Generation

Generated from Trainer

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

HachiML commited on Mar 3

Commit

27132e2

•

1 Parent(s): 504dd6a

Training in progress, step 100

Files changed (3) hide show

config.json +1 -1
model.safetensors +2 -2
training_args.bin +1 -1

config.json CHANGED Viewed

@@ -21,7 +21,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
   "transformers_version": "4.36.2",
   "use_cache": true,
   "vocab_size": 43176

   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
   "use_cache": true,
   "vocab_size": 43176

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944908962599a6309623f356e784a5d7a2997b01ae61d0934706b4dc1ed1772e
-size 492151048

 version https://git-lfs.github.com/spec/v1
+oid sha256:8b83c7f87ca6bd3fe0d449c5b831a18e8ef3a991d332912bb2cff76b01762caa
+size 246077736

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e2930f6d1300a32256d00f3ab1cd0177fefc6b5538515776e56d90e7827158
 size 4664

 version https://git-lfs.github.com/spec/v1
+oid sha256:b61539037ec445d4d6d2ba622da1d0180d6c0e5adcfeeeaba264e6eb157b42c9
 size 4664