Hugging Face's logo

golaxy
/
gogpt2-7b

Text Generation
Transformers
PyTorch
TensorBoard
4 datasets
Chinese
llama
llama2
chinese-llama2
gogpt2-7b
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
Chriskuei commited on
Commit
d5e09dd
•
1 Parent(s): 0a2a1d1

init v2.1

Browse files
Files changed (6) hide show
  1. config.json +2 -2
  2. pytorch_model-00001-of-00002.bin +1 -1
  3. pytorch_model-00002-of-00002.bin +1 -1
  4. tokenizer_config.json +1 -1
  5. trainer_state.json +0 -0
  6. training_args.bin +2 -2
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/data/searchgpt/yq/GoGPT/llama2-7b-sft-filterd-v3/ckpt",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -19,7 +19,7 @@
19
  "rms_norm_eps": 1e-05,
20
  "rope_scaling": null,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "bfloat16",
23
  "transformers_version": "4.29.1",
24
  "use_cache": false,
25
  "vocab_size": 68420
 
1
  {
2
+ "_name_or_path": "/data/searchgpt/yq/GoGPT/llama2-7b-sft-filterd-v3",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
19
  "rms_norm_eps": 1e-05,
20
  "rope_scaling": null,
21
  "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
  "transformers_version": "4.29.1",
24
  "use_cache": false,
25
  "vocab_size": 68420
pytorch_model-00001-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf4b76d57a5728dedf2b86d239cbe78f618f3d5f684d7e5fb4246b6eb5698a65
3
  size 14073577019
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1906a160b1e6d75d416987af40a7e113c95ef614108e6d6974776825d00059a6
3
  size 14073577019
pytorch_model-00002-of-00002.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae9c45cbbed2bca403551a593581e5244f75ccb2f54371b66926c2e51125fc04
3
  size 14073552151
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775d696506e6a5d3553d88cd1c63ada1e1b8fe7f6ab8f596c0a161951291aa2c
3
  size 14073552151
tokenizer_config.json CHANGED
@@ -18,7 +18,7 @@
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
- "model_max_length": 1024,
22
  "pad_token": null,
23
  "padding_side": "right",
24
  "sp_model_kwargs": {},
 
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
+ "model_max_length": 4096,
22
  "pad_token": null,
23
  "padding_side": "right",
24
  "sp_model_kwargs": {},
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47a4ef7d2f288e24e3e3dd54805a3352e4cd4ad83c7b915b322d6114212649e7
3
- size 4667
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f3ce69b22d8bea9970ef1930c06411acd75ef4919e13b70da79939eaa1d3d75
3
+ size 4987