ButteredToast commited on
Commit
4ce1322
·
1 Parent(s): bf6702e

Upload model

Browse files
Files changed (3) hide show
  1. README.md +1 -1
  2. config.json +47 -45
  3. model.safetensors +3 -0
README.md CHANGED
@@ -2,4 +2,4 @@
2
  tags:
3
  - AutoModelForCausalLM
4
  license: unlicense
5
- ---
 
2
  tags:
3
  - AutoModelForCausalLM
4
  license: unlicense
5
+ ---
config.json CHANGED
@@ -1,45 +1,47 @@
1
- {
2
- "_num_labels": 1,
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": 0.00001,
19
- "model_type": "gpt2",
20
- "n_ctx": 1024,
21
- "n_embd": 768,
22
- "n_head": 12,
23
- "n_inner": null,
24
- "n_layer": 12,
25
- "n_positions": 1024,
26
- "reorder_and_upcast_attn": false,
27
- "resid_pdrop": 0.1,
28
- "scale_attn_by_inverse_layer_idx": false,
29
- "scale_attn_weights": true,
30
- "summary_activation": null,
31
- "summary_first_dropout": 0.1,
32
- "summary_proj_to_labels": true,
33
- "summary_type": "cls_index",
34
- "summary_use_proj": true,
35
- "task_specific_params": {
36
- "text-generation": {
37
- "do_sample": true,
38
- "max_length": 50
39
- }
40
- },
41
- "torch_dtype": "float32",
42
- "transformers_version": "4.52.3",
43
- "use_cache": true,
44
- "vocab_size": 50257
45
- }
 
 
 
1
+ {
2
+ "_num_labels": 1,
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": 1024,
21
+ "n_embd": 768,
22
+ "n_head": 12,
23
+ "n_inner": null,
24
+ "n_layer": 6,
25
+ "n_positions": 1024,
26
+ "reorder_and_upcast_attn": false,
27
+ "resid_pdrop": 0.1,
28
+ "scale_attn_by_inverse_layer_idx": false,
29
+ "scale_attn_weights": true,
30
+ "summary_activation": null,
31
+ "summary_first_dropout": 0.1,
32
+ "summary_proj_to_labels": true,
33
+ "summary_type": "cls_index",
34
+ "summary_use_proj": true,
35
+ "task_specific_params": {
36
+ "text-generation": {
37
+ "do_sample": true,
38
+ "max_length": 40,
39
+ "temperature": 0.5,
40
+ "top_p": 0.9
41
+ }
42
+ },
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.52.3",
45
+ "use_cache": true,
46
+ "vocab_size": 50257
47
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8c53c325855690fca8fd918d94359f8e8c6e5a9a8fc7c1a6c2a5d3b9cd714c0
3
+ size 327657928