SauerkrautLM-UNA-SOLAR-Instruct
This is the model for SauerkrautLM-UNA-SOLAR-Instruct. I used mergekit to merge models.
🥳 As of December 24 2023, this model holds the first place position on the Open LLM Leaderboard.
Prompt Template(s)
### User:
{user}
### Assistant:
{asistant}
Yaml Config to reproduce
slices:
- sources:
- model: VAGOsolutions/SauerkrautLM-SOLAR-Instruct
layer_range: [0, 48]
- model: fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
layer_range: [0, 48]
merge_method: slerp
base_model: upstage/SOLAR-10.7B-Instruct-v1.0
parameters:
t:
- filter: self_attn
value: [0, 0.5, 0.3, 0.7, 1]
- filter: mlp
value: [1, 0.5, 0.7, 0.3, 0]
- value: 0.5 # fallback for rest of tensors
tokenizer_source: union
dtype: bfloat16
Quantizationed versions
Quantizationed versions of this model is available thanks to TheBloke.
GPTQ
GGUF
AWQ
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 74.26 |
| AI2 Reasoning Challenge (25-Shot) | 70.90 |
| HellaSwag (10-Shot) | 88.30 |
| MMLU (5-Shot) | 66.15 |
| TruthfulQA (0-shot) | 71.80 |
| Winogrande (5-shot) | 83.74 |
| GSM8k (5-shot) | 64.67 |
If you would like to support me: