Hugging Face's logo

onnx-community
/
gpt2-large-ONNX

Text Generation
Transformers.js
ONNX
gpt2
Model card Files
xet
Community
Felladrin commited on
Commit
ff2ce7c
·
verified ·
1 Parent(s): 4e6fc2d

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. .gitattributes +3 -0
  2. README.md +9 -0
  3. config.json +40 -0
  4. generation_config.json +6 -0
  5. merges.txt +0 -0
  6. onnx/model.onnx +3 -0
  7. onnx/model.onnx_data +3 -0
  8. onnx/model_bnb4.onnx +3 -0
  9. onnx/model_bnb4.onnx_data +3 -0
  10. onnx/model_fp16.onnx +3 -0
  11. onnx/model_int8.onnx +3 -0
  12. onnx/model_q4.onnx +3 -0
  13. onnx/model_q4.onnx_data +3 -0
  14. onnx/model_q4f16.onnx +3 -0
  15. onnx/model_quantized.onnx +3 -0
  16. onnx/model_uint8.onnx +3 -0
  17. quantize_config.json +18 -0
  18. special_tokens_map.json +5 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +20 -0
  21. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/model_bnb4.onnx_data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers.js
3
+ base_model:
4
+ - openai-community/gpt2-large
5
+ ---
6
+
7
+ # gpt2-large (ONNX)
8
+
9
+ This is an ONNX version of [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "openai-community/gpt2-large",
4
+ "activation_function": "gelu_new",
5
+ "architectures": [
6
+ "GPT2LMHeadModel"
7
+ ],
8
+ "attn_pdrop": 0.1,
9
+ "bos_token_id": 50256,
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 50256,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 1280,
17
+ "n_head": 20,
18
+ "n_inner": null,
19
+ "n_layer": 36,
20
+ "n_positions": 1024,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "torch_dtype": "float32",
37
+ "transformers_version": "4.49.0",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
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": "4.49.0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00e22a1ae8f284ea1365cdfc2cbbaf4099d641c731169ad5bd08a5f8aa69111
3
+ size 1022356
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfb77e435265792377c119ed22e316b083844b7f85a38b36fe7ca7df716c931
3
+ size 3096120320
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66330c69171d6a5161d557a220c9101a97bdef24de8f048445f024b09e7a1cf0
3
+ size 1024555
onnx/model_bnb4.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfb77e435265792377c119ed22e316b083844b7f85a38b36fe7ca7df716c931
3
+ size 3096120320
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43d3a96e8a3ecf694b9f01ba6cb863d28523d647a50fb7920198267ff682d8e8
3
+ size 1549071762
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5600a6c1349027c79e4578c5f71f65095b28a64383737dfa5dcbaa424018a75b
3
+ size 1034364626
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfe7d6ed94fbdb4e929fa5ea205942936db0f533c90d3a90506ecfa600fbd4fa
3
+ size 1023683
onnx/model_q4.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bfb77e435265792377c119ed22e316b083844b7f85a38b36fe7ca7df716c931
3
+ size 3096120320
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:172dbabce0f75689c0a0461f358f2f9b7ffaffb010bfc02bc66bb29b41dcf63c
3
+ size 1549071781
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5600a6c1349027c79e4578c5f71f65095b28a64383737dfa5dcbaa424018a75b
3
+ size 1034364626
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb726853830fe0c4f6a4f9bc431c88f1a1f0fa5affdc76f3882246d4729c492
3
+ size 1034364702
quantize_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "modes": [
3
+ "fp16",
4
+ "q8",
5
+ "int8",
6
+ "uint8",
7
+ "q4",
8
+ "q4f16",
9
+ "bnb4"
10
+ ],
11
+ "per_channel": false,
12
+ "reduce_range": false,
13
+ "block_size": null,
14
+ "is_symmetric": true,
15
+ "accuracy_level": null,
16
+ "quant_type": 1,
17
+ "op_block_list": null
18
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff