ai-modelscope
commited on
Commit
•
173fb40
1
Parent(s):
771d301
first commit
Browse files- .gitattributes +10 -11
- README.md +44 -3
- config.json +39 -0
- configuration.json +4 -0
- generation_config.json +7 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- quantize_config.json +11 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +53 -0
.gitattributes
CHANGED
@@ -1,35 +1,34 @@
|
|
1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
4 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
-
*.
|
35 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
5 |
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
|
|
6 |
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
|
|
11 |
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
13 |
*.onnx filter=lfs diff=lfs merge=lfs -text
|
14 |
*.ot filter=lfs diff=lfs merge=lfs -text
|
15 |
*.parquet filter=lfs diff=lfs merge=lfs -text
|
16 |
*.pb filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
17 |
*.pt filter=lfs diff=lfs merge=lfs -text
|
18 |
*.pth filter=lfs diff=lfs merge=lfs -text
|
19 |
*.rar filter=lfs diff=lfs merge=lfs -text
|
|
|
20 |
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
21 |
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
|
|
22 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
23 |
*.tgz filter=lfs diff=lfs merge=lfs -text
|
|
|
24 |
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
28 |
+
*.db* filter=lfs diff=lfs merge=lfs -text
|
29 |
+
*.ark* filter=lfs diff=lfs merge=lfs -text
|
30 |
+
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
31 |
+
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
32 |
+
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
33 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
34 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
@@ -1,3 +1,44 @@
|
|
1 |
-
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- zh
|
5 |
+
pipeline_tag: text-generation
|
6 |
+
tags:
|
7 |
+
- gptq
|
8 |
+
- int4
|
9 |
+
- yi1.5-34B-Chat
|
10 |
+
- pytorch
|
11 |
+
license: apache-2.0
|
12 |
+
license_name: apache-2.0
|
13 |
+
license_link: LICENSE
|
14 |
+
---
|
15 |
+
|
16 |
+
## About Quantization
|
17 |
+
我们使用modelscope [swift](https://github.com/modelscope/swift/)仓库进行GPTQ 4bit量化. 量化文档可以查看[这里](https://github.com/modelscope/swift/blob/main/docs/source/LLM/LLM%E9%87%8F%E5%8C%96%E6%96%87%E6%A1%A3.md). 量化命令如下:
|
18 |
+
|
19 |
+
We use the modelscope [swift](https://github.com/modelscope/swift/) repository to perform GPTQ 4bit quantization. Quantization documentation can be found [here](https://github.com/modelscope/swift/blob/main/docs/source_en/LLM/LLM-quantization.md). The quantization command is as follows:
|
20 |
+
|
21 |
+
```bash
|
22 |
+
# Experimental Environment: A100
|
23 |
+
OMP_NUM_THREADS=14 \
|
24 |
+
swift export \
|
25 |
+
--quant_bits 4 \
|
26 |
+
--model_type yi-1_5-34b-chat \
|
27 |
+
--quant_method gptq \
|
28 |
+
--dataset alpaca-zh alpaca-en sharegpt-gpt4-mini \
|
29 |
+
--quant_seqlen 4096
|
30 |
+
```
|
31 |
+
|
32 |
+
Inference:
|
33 |
+
```bash
|
34 |
+
CUDA_VISIBLE_DEVICES=0 swift infer --model_type yi-1_5-34b-chat-gptq-int4
|
35 |
+
```
|
36 |
+
|
37 |
+
SFT:
|
38 |
+
```bash
|
39 |
+
CUDA_VISIBLE_DEVICES=0 swift sft --model_type yi-1_5-34b-chat-gptq-int4 --dataset leetcode-python-en
|
40 |
+
```
|
41 |
+
|
42 |
+
Original Model:
|
43 |
+
|
44 |
+
[YI1.5-34B-Chat](https://modelscope.cn/models/01ai/Yi-1.5-34B-Chat/summary)
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/mnt/workspace/.cache/modelscope/01ai/Yi-1___5-34B-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 7168,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 20480,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 56,
|
17 |
+
"num_hidden_layers": 60,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"quantization_config": {
|
22 |
+
"bits": 4,
|
23 |
+
"damp_percent": 0.1,
|
24 |
+
"desc_act": false,
|
25 |
+
"group_size": 128,
|
26 |
+
"modules_in_block_to_quantize": null,
|
27 |
+
"quant_method": "gptq",
|
28 |
+
"sym": true,
|
29 |
+
"true_sequential": true
|
30 |
+
},
|
31 |
+
"rms_norm_eps": 1e-06,
|
32 |
+
"rope_scaling": null,
|
33 |
+
"rope_theta": 5000000.0,
|
34 |
+
"tie_word_embeddings": false,
|
35 |
+
"torch_dtype": "float16",
|
36 |
+
"transformers_version": "4.39.3",
|
37 |
+
"use_cache": false,
|
38 |
+
"vocab_size": 64000
|
39 |
+
}
|
configuration.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"framework": "Pytorch",
|
3 |
+
"task": "text-generation"
|
4 |
+
}
|
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": "4.40.0"
|
7 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbdf30d17622f9c3e5a7e27d5a6568a819eeced05f8e5428c1f56eeadb2886da
|
3 |
+
size 9975871168
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:accc540d29a3f73328f7f9263f7eb6f0e7ab5044a600f849f084b49c13204b75
|
3 |
+
size 9273093736
|
model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
quantize_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bits": 4,
|
3 |
+
"dataset": "alpaca-zh,alpaca-en,sharegpt-gpt4:default",
|
4 |
+
"group_size": 128,
|
5 |
+
"damp_percent": 0.1,
|
6 |
+
"desc_act": false,
|
7 |
+
"sym": true,
|
8 |
+
"true_sequential": true,
|
9 |
+
"quant_method": "gptq",
|
10 |
+
"modules_in_block_to_quantize": null
|
11 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
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": "<|startoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "<|endoftext|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"7": {
|
31 |
+
"content": "<|im_end|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
}
|
38 |
+
},
|
39 |
+
"bos_token": "<|startoftext|>",
|
40 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
|
41 |
+
"clean_up_tokenization_spaces": false,
|
42 |
+
"eos_token": "<|im_end|>",
|
43 |
+
"legacy": true,
|
44 |
+
"model_max_length": 4096,
|
45 |
+
"pad_token": "<unk>",
|
46 |
+
"padding_side": "right",
|
47 |
+
"sp_model_kwargs": {},
|
48 |
+
"spaces_between_special_tokens": false,
|
49 |
+
"split_special_tokens": false,
|
50 |
+
"tokenizer_class": "LlamaTokenizer",
|
51 |
+
"unk_token": "<unk>",
|
52 |
+
"use_default_system_prompt": false
|
53 |
+
}
|