Hugging Face's logo

BreadAi
/
DiscordPy

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Model card Files
xet
 Community
4
breadlicker45 commited on
Commit
15da977
·
1 Parent(s): f379b29

Upload 5 files

Browse files
Files changed (5) hide show
  1. config.json +25 -18
  2. generation_config.json +2 -2
  3. merges.txt +0 -0
  4. pytorch_model.bin +2 -2
  5. vocab.json +0 -0
config.json CHANGED
@@ -1,26 +1,33 @@
1
  {
2
- "_name_or_path": "EleutherAI/pythia-160m",
 
3
  "architectures": [
4
- "GPTNeoXForCausalLM"
5
  ],
6
- "bos_token_id": 0,
7
- "eos_token_id": 0,
8
- "hidden_act": "gelu",
9
- "hidden_size": 768,
10
  "initializer_range": 0.02,
11
- "intermediate_size": 3072,
12
- "layer_norm_eps": 1e-05,
13
- "line_by_line": true,
14
- "max_position_embeddings": 2048,
15
- "model_type": "gpt_neox",
16
- "num_attention_heads": 12,
17
- "num_hidden_layers": 12,
18
- "rotary_emb_base": 10000,
19
- "rotary_pct": 0.25,
20
- "tie_word_embeddings": false,
 
 
 
 
 
 
 
21
  "torch_dtype": "float32",
22
  "transformers_version": "4.26.1",
23
  "use_cache": true,
24
- "use_parallel_residual": true,
25
- "vocab_size": 50304
26
  }
 
1
  {
2
+ "_name_or_path": "cerebras/Cerebras-GPT-256M",
3
+ "activation_function": "gelu",
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.0,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.0,
10
+ "eos_token_id": 50256,
11
  "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "line_by_line": false,
14
+ "model_type": "gpt2",
15
+ "n_embd": 1088,
16
+ "n_head": 17,
17
+ "n_inner": 4352,
18
+ "n_layer": 14,
19
+ "n_positions": 2048,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.0,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.26.1",
31
  "use_cache": true,
32
+ "vocab_size": 50257
 
33
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "eos_token_id": 0,
5
  "transformers_version": "4.26.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
  "transformers_version": "4.26.1"
6
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e60bada7d389a77ee19b24b117b72423b480f23bb7c76555258a188da269ffd
3
- size 699685293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e0b35c41e04803c309d509d75183e085279c41b19afad991d81125cbc6ed925
3
+ size 1082693357
vocab.json ADDED
The diff for this file is too large to render. See raw diff