Upload folder using huggingface_hub
Browse files- README.md +9 -0
- config.json +32 -0
- generation_config.json +7 -0
- onnx/model.onnx +3 -0
- onnx/model_bnb4.onnx +3 -0
- onnx/model_fp16.onnx +3 -0
- onnx/model_int8.onnx +3 -0
- onnx/model_q4.onnx +3 -0
- onnx/model_q4f16.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- onnx/model_uint8.onnx +3 -0
- quantize_config.json +18 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers.js
|
3 |
+
base_model:
|
4 |
+
- Maykeye/TinyLLama-v0
|
5 |
+
---
|
6 |
+
|
7 |
+
# TinyLLama-v0 (ONNX)
|
8 |
+
|
9 |
+
This is an ONNX version of [Maykeye/TinyLLama-v0](https://huggingface.co/Maykeye/TinyLLama-v0). It was automatically converted and uploaded using [this space](https://huggingface.co/spaces/onnx-community/convert-to-onnx).
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_attn_implementation_autoset": true,
|
3 |
+
"_name_or_path": "Maykeye/TinyLLama-v0",
|
4 |
+
"architectures": [
|
5 |
+
"LlamaForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_bias": false,
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"head_dim": 4,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 64,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 256,
|
16 |
+
"max_position_embeddings": 2048,
|
17 |
+
"mlp_bias": false,
|
18 |
+
"model_type": "llama",
|
19 |
+
"num_attention_heads": 16,
|
20 |
+
"num_hidden_layers": 8,
|
21 |
+
"num_key_value_heads": 16,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"pretraining_tp": 1,
|
24 |
+
"rms_norm_eps": 1e-06,
|
25 |
+
"rope_scaling": null,
|
26 |
+
"rope_theta": 10000.0,
|
27 |
+
"tie_word_embeddings": false,
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.49.0",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 32000
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.49.0"
|
7 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1762ed7eac85941092e98a9c344f25f3e23b931a32f1e29695f8ebb537c7883
|
3 |
+
size 18648570
|
onnx/model_bnb4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:694924b22dcfba518a3c378563178c2e1821078b9344a02067cf7ae0dd3c8ed7
|
3 |
+
size 9814986
|
onnx/model_fp16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6108b7a5e2efa059c44b731bc4f67174a908d1888d9ffec0b948d8258bb57d87
|
3 |
+
size 9411848
|
onnx/model_int8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:885b2feeda265d134e9a9149bb0b3616ae420255cdbd7064484c31c163aa3d7e
|
3 |
+
size 4849458
|
onnx/model_q4.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:060bd81d8c30df6ea591e95c8349f6419a804a5b8bace6efff8d9c0d5564f14c
|
3 |
+
size 9975347
|
onnx/model_q4f16.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e9bd4ab9f79e79a36e3481f83a14c84343c0bdf2f2955dcb2afa634308fc989
|
3 |
+
size 5722497
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:885b2feeda265d134e9a9149bb0b3616ae420255cdbd7064484c31c163aa3d7e
|
3 |
+
size 4849458
|
onnx/model_uint8.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f84bde4f2f0a3c672d15afa9a533503cfee17deae0afb7c1ddbe86df9c8a908f
|
3 |
+
size 4849488
|
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 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"extra_special_tokens": {},
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": null,
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|