Hugging Face's logo

cuba6112
/
orion

Question Answering
Transformers
TensorBoard
Safetensors
English
gpt2
text-generation
fine-tuned
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
cuba6112 commited on
Commit
b3ca538
•
1 Parent(s): 4e443f0

Upload model

Browse files
Files changed (4) hide show
  1. README.md +1 -2
  2. config.json +39 -39
  3. generation_config.json +6 -6
  4. model.safetensors +1 -1
README.md CHANGED
@@ -1,11 +1,10 @@
1
-
2
  ---
3
  language: en
 
4
  tags:
5
  - gpt2
6
  - question-answering
7
  - fine-tuned
8
- license: mit
9
  ---
10
 
11
  # Fine-tuned Orion Model for Question Answering
 
 
1
  ---
2
  language: en
3
+ license: mit
4
  tags:
5
  - gpt2
6
  - question-answering
7
  - fine-tuned
 
8
  ---
9
 
10
  # Fine-tuned Orion Model for Question Answering
config.json CHANGED
@@ -1,39 +1,39 @@
1
- {
2
- "_name_or_path": "cuba6112/orion",
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
- "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
19
- "n_positions": 1024,
20
- "reorder_and_upcast_attn": false,
21
- "resid_pdrop": 0.1,
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
- "task_specific_params": {
30
- "text-generation": {
31
- "do_sample": true,
32
- "max_length": 50
33
- }
34
- },
35
- "torch_dtype": "float32",
36
- "transformers_version": "4.42.4",
37
- "use_cache": false,
38
- "vocab_size": 50257
39
- }
 
1
+ {
2
+ "_name_or_path": "./fine_tuned_orion",
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
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
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
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.40.0",
37
+ "use_cache": false,
38
+ "vocab_size": 50257
39
+ }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.42.4"
6
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.40.0"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc39b023e77ebe2a08a275d8cbda732bedefe8b973b7b9d21e1c4ce892397a5a
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86ced576468c80179044bf521584ca483b4d9b0d9f7c17a891f15818ccc52a82
3
  size 497774208