Llama
Collection
Meta-based models
•
945 items
•
Updated
•
1
Merge
This is a merge of pre-trained language models created using mergekit.
Merge Method
This model was merged using the Passthrough merge method using deepseek-ai/DeepSeek-R1-Distill-Llama-8B + mpasila/Llama-3.1-Literotica-LoRA-8B as a base.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B+mpasila/Llama-3.1-Literotica-LoRA-8B
dtype: bfloat16
merge_method: passthrough
models:
- model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B+mpasila/Llama-3.1-Literotica-LoRA-8B
tokenizer_source: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 17.84 |
| IFEval (0-Shot) | 18.85 |
| BBH (3-Shot) | 19.23 |
| MATH Lvl 5 (4-Shot) | 35.20 |
| GPQA (0-shot) | 7.05 |
| MuSR (0-shot) | 6.72 |
| MMLU-PRO (5-shot) | 19.97 |
- Downloads last month
- 35
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for Triangle104/DSR1-Distill-Llama-Lit-8B
Merge model
this model
Collections including Triangle104/DSR1-Distill-Llama-Lit-8B
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard18.850
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard19.230
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard35.200
- acc_norm on GPQA (0-shot)Open LLM Leaderboard7.050
- acc_norm on MuSR (0-shot)Open LLM Leaderboard6.720
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard19.970