|
--- |
|
license: other |
|
language: |
|
- en |
|
base_model: |
|
- ChaoticNeutrals/Sekhmet_Gimmel-L3.1-8B-v0.3 |
|
--- |
|
|
|
[NitralAI's measurement.json](https://huggingface.co/Nitral-AI/Sekhmet_Gimmel-L3.1-8B-v0.3-5bpw-exl2/blob/main/measurement.json) was used for quantization |
|
|
|
## **Sekhmet_Gimmel-L3.1-8B-v0.3** |
|
[exllamav2](https://github.com/turboderp/exllamav2) quant for [ChaoticNeutrals/Sekhmet_Gimmel-L3.1-8B-v0.3](https://huggingface.co/ChaoticNeutrals/Sekhmet_Gimmel-L3.1-8B-v0.3) |
|
|
|
**Original model information:** |
|
|
|
 |
|
|
|
# Sekhmet_Gimmel [v0.3] - Designed to provide robust solutions to complex problems while offering support and insightful guidance. |
|
|
|
# GGUF Quant's available thanks to: Soon <3 [GGUF Here]() |
|
# Additional GGUF Quant's available thanks to: Soon <3 [GGUF Here]() |
|
# EXL2 Quant: [5bpw Exl2 Here]() |
|
|
|
# Recomended ST Presets: [Sekhmet Presets(Same as Hathor's)](https://huggingface.co/Nitral-AI/Hathor_Presets/tree/main) |
|
--- |
|
# Training Note: Sekhmet_Gimmel [v0.3] is trained on: 1.5 epoch's of Private - Hathor_0.85 Instructions, small subset of creative writing data, roleplaying chat pairs over Sekhmet_Aleph-L3.1-8B-v0.2 |
|
# Additional Note's: This model was quickly assembled to provide users with a relatively uncensored alternative to L3.1 Instruct, featuring extended context capabilities. I do not expect it to match the performance levels demonstrated by Hathor_Tahsin version 0.9. |
