Hugging Face's logo

rungao2001
/
vicuna-7b-v1.5_deita10k_sft_full

Text Generation
Transformers
Safetensors
English
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community

Model Card for Model ID

Model Details

Model Description

This model is SFT by HuggingFaceH4/deita-10k-v0-sft dataset on lmsys/vicuna-7b-v1.5 model.

  • Model type: Llama2 Decoder-Only
  • Language(s) (NLP): English
  • License: llama2
  • Finetuned from model: lmsys/vicuna-7b-v1.5

Training Details

Training Data

HuggingFaceH4/deita-10k-v0-sft

Training Procedure

SFT

Notice: do_sample in generation_config.json was set to True to avoid this error https://github.com/huggingface/transformers/issues/29988.

Training Hyperparameters

  • Precision: BFloat16
  • Chat Template: Vicuna 1.1
  • Global Batch Size: 128
  • Learning Rate: 2.0e-5
  • Num Epoches: 3
  • Max Length: 2048
  • Packing: True
  • Training Steps 1047

Evaluation

It Finally achieved loss=0.8375901579856873 in the eval set of HuggingFaceH4/deita-10k-v0-sft

Testing Data, Factors & Metrics

Downloads last month
7
Safetensors
Model size
6.74B params
Tensor type
BF16
·
Inference Examples
Text Generation
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Dataset used to train rungao2001/vicuna-7b-v1.5_deita10k_sft_full