Dev #129

aJupyter · 2024-03-23T11:20:39Z

No description provided.

allow user to load embedding & rerank models from cache

embedding_path = os.path.join(model_dir, 'embedding_model') rerank_path = os.path.join(model_dir, 'rerank_model')

两个母亲多轮对话数据集合并、清理和去重之后，得到 2439 条多轮对话数据（每条有6-8轮对话）。

Add time print information save duplicate dataset as well remove print(content)

…10_M_1e4_32_64.py

three methods to load model 1. download model in openxlab 2. download model in modelscope 3. offline model

InternLM2 7B Base QLoRA 微调指南

zealot52099 and others added 14 commits March 22, 2024 20:15

Add files via upload

0aa5837

allow user to load embedding & rerank models from cache

Add files via upload

b7da9a6

embedding_path = os.path.join(model_dir, 'embedding_model') rerank_path = os.path.join(model_dir, 'rerank_model')

update rag/src/data_processing.py & rag/src/config/config.py (#123)

a8cfdb8

Add files via upload

dd7b6c4

两个母亲多轮对话数据集合并、清理和去重之后，得到 2439 条多轮对话数据（每条有6-8轮对话）。

optimize deduplicate.py

950cab0

Add time print information save duplicate dataset as well remove print(content)

add base model qlora fintuning config file: internlm2_7b_base_qlora_e…

252adc7

…10_M_1e4_32_64.py

add full finetune code from internlm2

df81a99

other 2 configs for base model

0124001

update cli_internlm2.py

a22ec59

three methods to load model 1. download model in openxlab 2. download model in modelscope 3. offline model

create upload_modelscope.py

affd90b

add base model and update personal contributions

6e0042a

Create README_internlm2_7b_base_qlora.md

383789e

InternLM2 7B Base QLoRA 微调指南

Add files via upload (#127)

c4187b6

add base model qlora fintuning config file and optimize deduplicate.py (

a12a7ef

#128)

aJupyter merged commit 2851a70 into main Mar 23, 2024

Provide feedback