From 73f4040abb8e4cf3f92bc577d161611cea78b652 Mon Sep 17 00:00:00 2001
From: JustinLin610
Date: Tue, 12 Sep 2023 23:10:59 +0800
Subject: [PATCH 1/3] add gradient checkpointing
---
finetune/finetune_lora_ds.sh | 1 +
finetune/finetune_lora_single_gpu.sh | 1 +
finetune/finetune_qlora_ds.sh | 1 +
finetune/finetune_qlora_single_gpu.sh | 1 +
4 files changed, 4 insertions(+)
diff --git a/finetune/finetune_lora_ds.sh b/finetune/finetune_lora_ds.sh
index 12efc6e..d877030 100644
--- a/finetune/finetune_lora_ds.sh
+++ b/finetune/finetune_lora_ds.sh
@@ -44,4 +44,5 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
--model_max_length 2048 \
--lazy_preprocess True \
--use_lora \
+ --gradient_checkpointing \
--deepspeed finetune/ds_config_zero2.json
\ No newline at end of file
diff --git a/finetune/finetune_lora_single_gpu.sh b/finetune/finetune_lora_single_gpu.sh
index 47b7237..9333b7d 100644
--- a/finetune/finetune_lora_single_gpu.sh
+++ b/finetune/finetune_lora_single_gpu.sh
@@ -32,4 +32,5 @@ python finetune.py \
--report_to "none" \
--model_max_length 2048 \
--lazy_preprocess True \
+ --gradient_checkpointing \
--use_lora
\ No newline at end of file
diff --git a/finetune/finetune_qlora_ds.sh b/finetune/finetune_qlora_ds.sh
index debea4f..58c05e9 100644
--- a/finetune/finetune_qlora_ds.sh
+++ b/finetune/finetune_qlora_ds.sh
@@ -46,4 +46,5 @@ torchrun $DISTRIBUTED_ARGS finetune.py \
--lazy_preprocess True \
--use_lora \
--q_lora \
+ --gradient_checkpointing \
--deepspeed finetune/ds_config_zero2.json
\ No newline at end of file
diff --git a/finetune/finetune_qlora_single_gpu.sh b/finetune/finetune_qlora_single_gpu.sh
index 3b89ee4..bf65b9f 100644
--- a/finetune/finetune_qlora_single_gpu.sh
+++ b/finetune/finetune_qlora_single_gpu.sh
@@ -32,5 +32,6 @@ python finetune.py \
--report_to "none" \
--model_max_length 2048 \
--lazy_preprocess True \
+ --gradient_checkpointing \
--use_lora \
--q_lora
\ No newline at end of file
From fb52dd330837638afd65fb332c523d83c451966f Mon Sep 17 00:00:00 2001
From: Junyang Lin
Date: Wed, 13 Sep 2023 16:53:34 +0800
Subject: [PATCH 2/3] Update README.md
---
README.md | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/README.md b/README.md
index 757ab30..7f1ec7e 100644
--- a/README.md
+++ b/README.md
@@ -15,6 +15,10 @@
+__Will be back soon...__
+
+---
+
We opensource **Qwen-7B** and **Qwen-7B-Chat** on both **🤖 ModelScope** and **🤗 Hugging Face** (Click the logos on top to the repos with codes and checkpoints). This repo includes the brief introduction to Qwen-7B, the usage guidance, and also a technical memo [link](tech_memo.md) that provides more information.
Qwen-7B is the 7B-parameter version of the large language model series, Qwen (abbr. Tongyi Qianwen), proposed by Alibaba Cloud. Qwen-7B is a Transformer-based large language model, which is pretrained on a large volume of data, including web texts, books, codes, etc. Additionally, based on the pretrained Qwen-7B, we release Qwen-7B-Chat, a large-model-based AI assistant, which is trained with alignment techniques. The features of the Qwen-7B series include:
From 0e07532cd0a28ca3e3af1850b8297bc095e44749 Mon Sep 17 00:00:00 2001
From: Dayiheng Liu <2689514749@qq.com>
Date: Fri, 15 Sep 2023 10:03:22 +0800
Subject: [PATCH 3/3] Update EVALUATION.md
fix typo
---
eval/EVALUATION.md | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/eval/EVALUATION.md b/eval/EVALUATION.md
index 1381e69..75ea021 100644
--- a/eval/EVALUATION.md
+++ b/eval/EVALUATION.md
@@ -59,7 +59,7 @@ pip install -e human-eval
python evaluate_humaneval.py -f HumanEval.jsonl -o HumanEval_res.jsonl
evaluate_functional_correctness HumanEval_res.jsonl
# Qwen-7B-Chat
-python evaluate_chat_mmlu.py -f HumanEval.jsonl -o HumanEval_res_chat.jsonl
+python evaluate_chat_humaneval.py -f HumanEval.jsonl -o HumanEval_res_chat.jsonl
evaluate_functional_correctness HumanEval_res_chat.jsonl
```