Hugging Face's logo

CrabfishAI
/
NeXGen-based

Text Generation
Transformers
PyTorch
TensorFlow
JAX
Rust
Safetensors
English
gpt2
Trained with AutoTrain
text-generation-inference
Model card Files
xet
Community
Sirclavin commited on
Commit
1cc6cea
·
1 Parent(s): 720f195

Upload 11 files

Browse files
Files changed (11) hide show
  1. config.json +33 -0
  2. flax_model.msgpack +3 -0
  3. generation_config.json +6 -0
  4. generation_config_for_text_generation.json +8 -0
  5. merges.txt +0 -0
  6. model.safetensors +3 -0
  7. pytorch_model.bin +3 -0
  8. rust_model.ot +3 -0
  9. tf_model.h5 +3 -0
  10. tokenizer.json +0 -0
  11. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 1024,
15
+ "n_head": 16,
16
+ "n_layer": 24,
17
+ "n_positions": 1024,
18
+ "n_special": 0,
19
+ "predict_special_tokens": true,
20
+ "resid_pdrop": 0.1,
21
+ "summary_activation": null,
22
+ "summary_first_dropout": 0.1,
23
+ "summary_proj_to_labels": true,
24
+ "summary_type": "cls_index",
25
+ "summary_use_proj": true,
26
+ "task_specific_params": {
27
+ "text-generation": {
28
+ "do_sample": true,
29
+ "max_length": 50
30
+ }
31
+ },
32
+ "vocab_size": 50257
33
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f48d00703d1aa3125c8767f0850a78fd7ae7d0ac9f644e2e3d1d0adb966dbc8a
3
+ size 1419302302
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.27.0.dev0"
6
+ }
generation_config_for_text_generation.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "do_sample": true,
5
+ "eos_token_id": 50256,
6
+ "max_length": 50,
7
+ "transformers_version": "4.27.0.dev0"
8
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc5a354a19255ad494f3d71549390baca1ccf61d1d822b9408971705c687c9cd
3
+ size 1519984962
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98c7b0558df2c732799e509a8157d392251b3a6b06e2c72eefb3a00eb10f8318
3
+ size 1520013706
rust_model.ot ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:064e9fde8e3a539c41b186a6ca94e6fb7c6520f49f903fb236f6e89912fedd32
3
+ size 1725881760
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d24e0340bdf3515551d7a6315b4048e33e9c7cb31b11c9fb11683234208fc56a
3
+ size 1419628976
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff