metadata
library_name: peft
license: llama2
datasets:
- vicgalle/alpaca-gpt4
language:
- en
pipeline_tag: text-generation
tags:
- llama-2
- llama
- instruct
- instruction
Info
Adapter model trained with the QloRA technique
- 📜 Model license: Llama 2 Community License Agreement
- 🏛️ Base Model: Llama-2-70b-hf
- 🖥️ Machine: Nvidia A100 (40 GB vRAM)
- 💵 Cost: $3.5
- ⌛ Training Time: 3 hour 22 minutes
- 📊 Dataset Used: vicgalle/alpaca-gpt4
Evulation Results (Open LLM Leaderboard)
| Average | ARC (25-shot) | HellaSwag (10-shot) | MMLU (5-shot) | TruthfulQA (0-shot) | |
|---|---|---|---|---|---|
| Scores | 67.3 | 66.38 | 84.51 | 62.75 | 55.57 |
💪 Our current ranking on Open LLM Leaderboard is 13.
Loss Graph
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