Downloads · 30 days
27
8% of all-time downloads
quantized-llama2-alpaca
NouRed/quantized-llama2-alpaca
quantized-llama2-alpaca is a text generation model from NouRed. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as mit.
quantized-llama2-alpaca is a fine-tuned version of the LLaMA2 (Llama-2-7b-hf) model on the Alpaca dataset using QLoRA.
All-time downloads
344
Public
Repo size
640 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin640 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 21, 2023
- Updated
- Sep 19, 2023
- SHA
- 14fcd2e3
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Quantized LLaMA2
quantized-llama2-alpaca is a fine-tuned version of the LLaMA2 (Llama-2-7b-hf) model on the Alpaca dataset using QLoRA.
Training procedure
The following bitsandbytes quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
Framework versions
- PEFT 0.4.0
- Task
- Text Generation
- Library
- peft
- License
- mit
- Created
- Aug 21, 2023
- Updated
- Sep 19, 2023