Downloads · 30 days
23
8% of all-time downloads
Llama-2-13b-hf-eli5-wiki-1024_r_64_alpha_16
dhmeltzer/Llama-2-13b-hf-eli5-wiki-1024_r_64_alpha_16
Llama-2-13b-hf-eli5-wiki-1024_r_64_alpha_16 is a machine learning model from dhmeltzer. Use it for the machine learning task on the model card, and read the license before you ship it in a product. 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
271
Public
Repo size
10 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1 GB · 50%
At a glance
- Library
- peft
- Access
- Public
- Created
- Sep 4, 2023
- Updated
- Nov 17, 2023
- SHA
- e6daf547
Base models
Model card
From the Hugging Face model README
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: True
- bnb_4bit_compute_dtype: bfloat16
Framework versions
- PEFT 0.4.0
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 47.39 |
| ARC (25-shot) | 59.98 |
| HellaSwag (10-shot) | 82.43 |
| MMLU (5-shot) | 55.41 |
| TruthfulQA (0-shot) | 39.9 |
| Winogrande (5-shot) | 76.56 |
| GSM8K (5-shot) | 10.54 |
| DROP (3-shot) | 6.89 |
- Library
- peft
- Created
- Sep 4, 2023
- Updated
- Nov 17, 2023