Hugging Face's logo

onnx-community
/
gpt2-xl-ONNX

Text Generation
Transformers.js
ONNX
gpt2
Model card Files
xet
Community
Felladrin commited on
Commit
045d09c
·
verified ·
1 Parent(s): 91c2250

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. .gitattributes +5 -0
  2. README.md +9 -0
  3. config.json +41 -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_fp16.onnx_data +3 -0
  12. onnx/model_int8.onnx +3 -0
  13. onnx/model_q4.onnx +3 -0
  14. onnx/model_q4.onnx_data +3 -0
  15. onnx/model_q4f16.onnx +3 -0
  16. onnx/model_q4f16.onnx_data +3 -0
  17. onnx/model_quantized.onnx +3 -0
  18. onnx/model_uint8.onnx +3 -0
  19. quantize_config.json +18 -0
  20. special_tokens_map.json +5 -0
  21. tokenizer.json +0 -0
  22. tokenizer_config.json +20 -0
  23. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/model_q4.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ onnx/model_q4f16.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-xl
5
+ ---
6
+
7
+ # gpt2-xl (ONNX)
8
+
9
+ This is an ONNX version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "openai-community/gpt2-xl",
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": 1600,
17
+ "n_head": 25,
18
+ "n_inner": null,
19
+ "n_layer": 48,
20
+ "n_positions": 1024,
21
+ "output_past": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.49.0",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
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 sha256:80c532e43acc91764916370311f114bdb82f8dea0e3e486d5cad4450dd54d886
3
+ size 1360037
onnx/model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7d4a5cfadb8969a7aa57aed8621d2fb6fb67346026fc5c8b22ee98e0acbcca
3
+ size 6230444800
onnx/model_bnb4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b77164fe9a2d21da7e87dc3dc0951f4125a63778278e3add83cf6230f70c59
3
+ size 1362956
onnx/model_bnb4.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7d4a5cfadb8969a7aa57aed8621d2fb6fb67346026fc5c8b22ee98e0acbcca
3
+ size 6230444800
onnx/model_fp16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6090e64bb5e24e40ed42b187bf1105aba80e2706fc4891200d737fd8d433e573
3
+ size 1384716
onnx/model_fp16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bb72887c262b687b09f218dc852b5c37fed71cb600ab8b61798c30a8a84c06
3
+ size 3115222400
onnx/model_int8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9714e2d65f41a1869c86dca7fbd4304e17f6fd9657415e745f2ea703d56949e
3
+ size 1883876457
onnx/model_q4.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c807908cfd2df66d0e270fdee1f04cf3e99a787a237fc8471f17a51d3bdd8d67
3
+ size 1361796
onnx/model_q4.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7d4a5cfadb8969a7aa57aed8621d2fb6fb67346026fc5c8b22ee98e0acbcca
3
+ size 6230444800
onnx/model_q4f16.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bfb82b7a26f53f9ccf8867e6b86aecd6aa26c1157147fbd1bb16cca6d754571
3
+ size 1385315
onnx/model_q4f16.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52bb72887c262b687b09f218dc852b5c37fed71cb600ab8b61798c30a8a84c06
3
+ size 3115222400
onnx/model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9714e2d65f41a1869c86dca7fbd4304e17f6fd9657415e745f2ea703d56949e
3
+ size 1883876457
onnx/model_uint8.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59f074690553ac4ee37fb386fd2a59b2365c9e41a8982adebbb0a365ee86fc86
3
+ size 1883876548
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