| | --- |
| | base_model: |
| | - TheDrummer/Llama-3SOME-8B-v2 |
| | - cgato/L3-TheSpice-8b-v0.8.3 |
| | - Sao10K/L3-8B-Stheno-v3.2 |
| | - SicariusSicariiStuff/Wingless_Imp_8B |
| | - deepseek-ai/DeepSeek-R1-Distill-Llama-8B |
| | - NeverSleep/Lumimaid-v0.2-8B |
| | library_name: transformers |
| | tags: |
| | - mergekit |
| | - merge |
| | license: cc-by-nc-4.0 |
| | --- |
| | # What is this? |
| |
|
| | A Llama3 model with Deepseek R1 Distill merge. Maybe it's not suit for RP? |
| |
|
| |  |
| |
|
| | Overall, this merge model is the best and smartest RP, ERP model. But the IFEval score is lower than other model, so I think it's wont follow well your instructions? I didn't test yet, will have a test later |
| |
|
| | <details> |
| | <summary>## Merge Detail</summary> |
| | <p> |
| | ### Models Merged |
| | |
| | The following models were included in the merge: |
| | * [TheDrummer/Llama-3SOME-8B-v2](https://huggingface.co/TheDrummer/Llama-3SOME-8B-v2) |
| | * [cgato/L3-TheSpice-8b-v0.8.3](https://huggingface.co/cgato/L3-TheSpice-8b-v0.8.3) |
| | * [Sao10K/L3-8B-Stheno-v3.2](https://huggingface.co/Sao10K/L3-8B-Stheno-v3.2) |
| | * [SicariusSicariiStuff/Wingless_Imp_8B](https://huggingface.co/SicariusSicariiStuff/Wingless_Imp_8B) |
| | * [deepseek-ai/DeepSeek-R1-Distill-Llama-8B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-8B) |
| |
|
| | ### Configuration |
| |
|
| | The following YAML configuration was used to produce this model: |
| |
|
| | ```yaml |
| | base_model: NeverSleep/Lumimaid-v0.2-8B |
| | merge_method: model_stock |
| | dtype: bfloat16 |
| | models: |
| | - model: cgato/L3-TheSpice-8b-v0.8.3 |
| | - model: Sao10K/L3-8B-Stheno-v3.2 |
| | - model: TheDrummer/Llama-3SOME-8B-v2 |
| | - model: SicariusSicariiStuff/Wingless_Imp_8B |
| | - model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B |
| | ``` |
| |
|
| | </p> |
| | </details> |
