423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-29 01:02:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

tiny fix

Browse Source 
Former-commit-id: 0048a2021e94d068f7c6054df0b9569ae4912eb1
This commit is contained in:
hiyouga 2024-03-06 17:25:08 +08:00
parent 8b6c178249
commit 31c618f1f7
4 changed files with 15 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -475,8 +475,7 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
#### Use Huggingface Accelerate
```bash
accelerate config # configure the environment
accelerate launch src/train_bash.py # arguments (same as above)
accelerate launch --config_file config.yaml src/train_bash.py # arguments (same as above)
```
<details><summary>Example config for LoRA training</summary>

3
README_zh.md
View File

@ -474,8 +474,7 @@ CUDA_VISIBLE_DEVICES=0 python src/train_bash.py \
#### 使用 Huggingface Accelerate
```bash
accelerate config # 首先配置分布式环境
accelerate launch src/train_bash.py # 参数同上
accelerate launch --config_file config.yaml src/train_bash.py # 参数同上
```
<details><summary>LoRA 训练的 Accelerate 配置示例</summary>

24
src/llmtuner/extras/constants.py
View File

@ -671,48 +671,48 @@ register_model_group(
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8",
},
"Qwen1.5-0.5B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-0.5B-Chat-GPTQ-Int4",
DownloadSource.DEFAULT: "Qwen/Qwen1.5-0.5B-Chat-AWQ",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-0.5B-Chat-AWQ",
},
"Qwen1.5-1.8B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8",
},
"Qwen1.5-1.8B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-1.8B-Chat-GPTQ-Int4",
DownloadSource.DEFAULT: "Qwen/Qwen1.5-1.8B-Chat-AWQ",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-1.8B-Chat-AWQ",
},
"Qwen1.5-4B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-4B-Chat-GPTQ-Int8",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-4B-Chat-GPTQ-Int8",
},
"Qwen1.5-4B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-4B-Chat-GPTQ-Int4",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-4B-Chat-GPTQ-Int4",
DownloadSource.DEFAULT: "Qwen/Qwen1.5-4B-Chat-AWQ",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-4B-Chat-AWQ",
},
"Qwen1.5-7B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-7B-Chat-GPTQ-Int8",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-7B-Chat-GPTQ-Int8",
},
"Qwen1.5-7B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-7B-Chat-GPTQ-Int4",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-7B-Chat-GPTQ-Int4",
DownloadSource.DEFAULT: "Qwen/Qwen1.5-7B-Chat-AWQ",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-7B-Chat-AWQ",
},
"Qwen1.5-14B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-14B-Chat-GPTQ-Int8",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-14B-Chat-GPTQ-Int8",
},
"Qwen1.5-14B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-14B-Chat-GPTQ-Int4",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-14B-Chat-GPTQ-Int4",
DownloadSource.DEFAULT: "Qwen/Qwen1.5-14B-Chat-AWQ",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-14B-Chat-AWQ",
},
"Qwen1.5-72B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-72B-Chat-GPTQ-Int8",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-72B-Chat-GPTQ-Int8",
},
"Qwen1.5-72B-int4-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen1.5-72B-Chat-GPTQ-Int4",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-72B-Chat-GPTQ-Int4",
DownloadSource.DEFAULT: "Qwen/Qwen1.5-72B-Chat-AWQ",
DownloadSource.MODELSCOPE: "qwen/Qwen1.5-72B-Chat-AWQ",
},
},
template="qwen",

2
src/llmtuner/train/sft/metric.py
View File

@ -11,7 +11,7 @@ if TYPE_CHECKING:
from transformers.tokenization_utils import PreTrainedTokenizer
if is_jieba_available():
import jieba
import jieba # type: ignore
if is_nltk_available():
from nltk.translate.bleu_score import SmoothingFunction, sentence_bleu