A newer version of this model is available:
sthenno-com/miscii-14b-1225
QuantFactory/miscii-14b-1028-GGUF
This is quantized version of sthenno-com/miscii-14b-1028 created using llama.cpp
Original Model Card
miscii-14b-1028
Role-based Instructions
Just parse the following as your system prompt.
Note there is NO special-tokens here.
An example system prompt:
system_prompt: str = (
"""<|context_start|>personas<|context_sep|>
<|persona_start|>user<|persona_sep|>
{user_persona}<|persona_end|>
<|persona_start|>assistant<|persona_sep|>
{assistant_persona}<|persona_end|><|context_end|>""".format(
user_persona="""I am Miscii.
I am the designer of Sthenno.
[Optional: Additional statements]""",
assistant_persona="""I am Sthenno.
I speak in Chinese.
[Optional: Additional statements]""",
)
)
Training
See Report for miscii-1020 for more details.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here.
| Metric | Value |
|---|---|
| Avg. | 35.05 |
| IFEval (0-Shot) | 82.37 |
| BBH (3-Shot) | 49.26 |
| MATH Lvl 5 (4-Shot) | 6.34 |
| GPQA (0-shot) | 14.21 |
| MuSR (0-shot) | 12.00 |
| MMLU-PRO (5-shot) | 46.14 |
- Downloads last month
- 325
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for QuantFactory/miscii-14b-1028-GGUF
Datasets used to train QuantFactory/miscii-14b-1028-GGUF
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard82.370
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard49.260
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard6.340
- acc_norm on GPQA (0-shot)Open LLM Leaderboard14.210
- acc_norm on MuSR (0-shot)Open LLM Leaderboard12.000
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard46.140