Downloads · 30 days
22
7% of all-time downloads
model-isha-qa
nateshmbhat/model-isha-qa
model-isha-qa is a text generation model from nateshmbhat. Use it when you need the model to write or continue text. It is set up for transformers.
- Base model : stabilityai/StableBeluga-13B - Quantization Used : 4 bit - Learning rate : 2e-4 - Batch Size : 2 - Epochs : 3 - Trainer : sft - Max token length : 2048 (capable of higher token length)
All-time downloads
294
Public
Repo size
52.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin26.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Aug 3, 2023
- Updated
- Aug 5, 2023
- SHA
- fd3d33b7
Try a prompt
Datasets
Model card
From the Hugging Face model README
ISHA Call Center QA Model
This model was trained on a finetuned version(StableBeluga2) of Llama2-13B from stabilityai : (StableBeluga2 tops the LLM leaderboard currently)
Dataset Used : https://huggingface.co/datasets/nateshmbhat/isha-qa-text
Train Params used :
- Base model : stabilityai/StableBeluga-13B
- Quantization Used : 4 bit
- Learning rate : 2e-4
- Batch Size : 2
- Epochs : 3
- Trainer : sft
- Max token length : 2048 (capable of higher token length)
!autotrain llm --train --project_name project-isha-qa --model stabilityai/StableBeluga-13B --data_path nateshmbhat/isha-qa-text --use_peft --use_int4 --learning_rate 2e-4 --train_batch_size 2 --num_train_epochs 3 --trainer sft --model_max_length 2048 --push_to_hub --repo_id nateshmbhat/model-isha-qa
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- Created
- Aug 3, 2023
- Updated
- Aug 5, 2023