Hugging Face's logo

AlexWortega
/
instruct_XGLM75k

Text Generation
Transformers
PyTorch
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
1
AlexWortega commited on
Commit
fb64177
•
1 Parent(s): 138400c

Upload model

Browse files
Files changed (3) hide show
  1. config.json +36 -21
  2. generation_config.json +3 -5
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,27 +1,42 @@
1
  {
2
- "_name_or_path": "ckpts11xglm/sft_0_60000",
3
- "activation_dropout": 0.0,
4
- "activation_function": "gelu",
5
  "architectures": [
6
- "XGLMForCausalLM"
7
  ],
8
- "attention_dropout": 0.1,
9
- "attention_heads": 16,
10
- "bos_token_id": 0,
11
- "d_model": 2048,
12
- "decoder_start_token_id": 2,
13
- "dropout": 0.1,
14
- "eos_token_id": 2,
15
- "ffn_dim": 8192,
16
- "init_std": 0.02,
17
- "layerdrop": 0.0,
18
- "max_position_embeddings": 2048,
19
- "model_type": "xglm",
20
- "num_layers": 24,
21
- "pad_token_id": 1,
22
- "scale_embedding": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  "torch_dtype": "float32",
24
- "transformers_version": "4.27.1",
25
  "use_cache": true,
26
- "vocab_size": 256013
27
  }
 
1
  {
2
+ "_name_or_path": "ckpts11/sft_0_70000/",
3
+ "activation_function": "gelu_new",
 
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "layer_norm_epsilon": 1e-05,
19
+ "model_type": "gpt2",
20
+ "n_ctx": 2048,
21
+ "n_embd": 1024,
22
+ "n_head": 16,
23
+ "n_inner": null,
24
+ "n_layer": 24,
25
+ "n_positions": 2048,
26
+ "n_special": 0,
27
+ "output_past": true,
28
+ "predict_special_tokens": true,
29
+ "reorder_and_upcast_attn": false,
30
+ "resid_pdrop": 0.1,
31
+ "scale_attn_by_inverse_layer_idx": false,
32
+ "scale_attn_weights": true,
33
+ "summary_activation": null,
34
+ "summary_first_dropout": 0.1,
35
+ "summary_proj_to_labels": true,
36
+ "summary_type": "cls_index",
37
+ "summary_use_proj": true,
38
  "torch_dtype": "float32",
39
+ "transformers_version": "4.26.1",
40
  "use_cache": true,
41
+ "vocab_size": 50263
42
  }
generation_config.json CHANGED
@@ -1,8 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "decoder_start_token_id": 2,
5
- "eos_token_id": 2,
6
- "pad_token_id": 1,
7
- "transformers_version": "4.27.1"
8
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.26.1"
 
 
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3c8adee1c9848ae5145115d8f6002f390f0061950e44728019b18bc03d14402
3
- size 6931791831
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b837ae1527bcc55004db32326152cff1b8b360cfda5827d516b71ee8dbcda8ee
3
+ size 1524285725