Hugging Face's logo

Multi-Domain-Expert-Learning
/
expert-min-pile-instruct

Text Generation
Transformers
PyTorch
gpt_neox
Generated from Trainer
text-generation-inference
Model card Files Community
2
P1ayer-1 commited on
Commit
cc05141
·
1 Parent(s): 3359129

Training in progress, step 500

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. pytorch_model.bin +2 -2
  3. tokenizer.json +0 -1
  4. training_args.bin +2 -2
config.json CHANGED
@@ -17,7 +17,7 @@
17
  "rotary_emb_base": 10000,
18
  "rotary_pct": 0.25,
19
  "tie_word_embeddings": false,
20
- "torch_dtype": "float32",
21
  "transformers_version": "4.28.1",
22
  "use_cache": true,
23
  "use_parallel_residual": true,
 
17
  "rotary_emb_base": 10000,
18
  "rotary_pct": 0.25,
19
  "tie_word_embeddings": false,
20
+ "torch_dtype": "float16",
21
  "transformers_version": "4.28.1",
22
  "use_cache": true,
23
  "use_parallel_residual": true,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e594dbaa75c36cbf7e4a34fe357363421b8aad7ae231521896723339cfe504d5
3
- size 4113910045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f8c41c9a4671e776bc28d3049a1477671e4e02c85575d05c7cddb103acf3e05
3
+ size 2090538933
tokenizer.json CHANGED
@@ -275,7 +275,6 @@
275
  "continuing_subword_prefix": null,
276
  "end_of_word_suffix": null,
277
  "fuse_unk": false,
278
- "byte_fallback": false,
279
  "vocab": {
280
  "<|endoftext|>": 0,
281
  "<|padding|>": 1,
 
275
  "continuing_subword_prefix": null,
276
  "end_of_word_suffix": null,
277
  "fuse_unk": false,
 
278
  "vocab": {
279
  "<|endoftext|>": 0,
280
  "<|padding|>": 1,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d7a9f8dc6992869b75949cdfa8dbd7afe456ee4f5e8f4f6f4ac3864cc9a00aa
3
- size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c48fe5038ba9667ac6ed496df6b0e3a7ac8168ab8c61b40b1a0a663158f631
3
+ size 4795