Downloads · 30 days
6
2% of all-time downloads
llama2-7b-qlora-openassistant-guanaco
juliensimon/llama2-7b-qlora-openassistant-guanaco
llama2-7b-qlora-openassistant-guanaco is a text generation model from juliensimon. Use it when you need the model to write or continue text. It is set up for peft.
This model was fine-tuned using 4-bit QLoRa, following the instructions in https://huggingface.co/blog/llama2fine-tuning-with-peft.
All-time downloads
300
Public
Repo size
134 MB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin134 MB · 98%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Oct 7, 2023
- Updated
- Oct 7, 2023
- SHA
- 4922acfe
Try a prompt
Base models
Model card
From the Hugging Face model README
This model was fine-tuned using 4-bit QLoRa, following the instructions in https://huggingface.co/blog/llama2#fine-tuning-with-peft.
The dataset includes 10k prompts.
I used a Amazon EC2 g5.xlarge instance (1xA10G GPU), with the Deep Learning AMI for PyTorch. Training time was about 10 hours. On-demand price is about $10, which can easily be reduced to about $3 with EC2 Spot Instances.
The full log is included, as well as a simple inference script.
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- 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: fp4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float32
Framework versions
- PEFT 0.5.0
- Task
- Text Generation
- Library
- peft
- Created
- Oct 7, 2023
- Updated
- Oct 7, 2023