Downloads · 30 days
0
Llama-3-8B-Instruct-750Mb-lora
REILX/Llama-3-8B-Instruct-750Mb-lora
Llama-3-8B-Instruct-750Mb-lora is a machine learning model from REILX. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as llama3.
Access
Public
Updated Jun 18, 2024
Repo size
42 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors42 MB · 82%
At a glance
- License
- llama3
- Access
- Public
- Created
- May 11, 2024
- Updated
- Jun 18, 2024
- SHA
- b722abef
Model card
From the Hugging Face model README
数据集
使用以下8个数据集
对Llama-3-8B-Instruct进行微调。
基础模型：
训练工具
https://github.com/hiyouga/LLaMA-Factory
测评方式：
使用opencompass(https://github.com/open-compass/OpenCompass/ )， 测试工具基于CEval和MMLU对微调之后的模型和原始模型进行测试。</br> 测试模型分别为：
- Llama-3-8B
- Llama-3-8B-Instruct
- Llama-3-8B-Instruct-750Mb-lora, 使用8DataSets数据集对Llama-3-8B-Instruct模型进行sft方式lora微调
测试机器
8*A800
8DataSets数据集：
大约750Mb的微调数据集
- https://huggingface.co/datasets/REILX/extracted_tagengo_gpt4
- https://huggingface.co/datasets/TigerResearch/sft_zh
- https://huggingface.co/datasets/silk-road/alpaca-data-gpt4-chinese
- https://huggingface.co/datasets/LooksJuicy/ruozhiba
- https://huggingface.co/datasets/microsoft/orca-math-word-problems-200k
- https://huggingface.co/datasets/alexl83/AlpacaDataCleaned
- https://huggingface.co/datasets/Sao10K/Claude-3-Opus-Instruct-5K
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 300
- num_epochs: 1.0
- License
- llama3
- Languages
- zh, en
- Created
- May 11, 2024
- Updated
- Jun 18, 2024