Downloads · 30 days
6
24% of all-time downloads
llama2-korquad-finetuning-da
solaris33/llama2-korquad-finetuning-da
llama2-korquad-finetuning-da is a text generation model from solaris33. Use it when you need the model to write or continue text. It is set up for peft.
The following bitsandbytes quantization config was used during training: - quantmethod: bitsandbytes - loadin8bit: False - loadin4bit: True - llmint8threshold: 6.0 - llmint8skipmodules: None - llmint8enablefp32cpuoffl…
All-time downloads
25
Public
Repo size
33.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin33.6 MB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- Oct 29, 2023
- Updated
- Oct 29, 2023
- SHA
- 8be2f5f4
Try a prompt
Base models
Model card
From the Hugging Face model README
Model Trained Using AutoTrain
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: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.6.0.dev0
- Task
- Text Generation
- Library
- peft
- Created
- Oct 29, 2023
- Updated
- Oct 29, 2023