Hugging Face's logo

grimjim
/
Llama-3-Oasis-v1-OAS-8B

Text Generation
Transformers
Safetensors
llama
mergekit
Merge
text-generation-inference
Inference Endpoints
Model card Files Community
grimjim commited on
Commit
b47e6c7
•
1 Parent(s): f4c0ed5

Update README.md

Browse files

Added sampler settings guidance

Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -21,8 +21,11 @@ Each merge component was already subjected to Orthogonal Activation Steering (OA
21
  - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS : focus on roleplay
22
  - Hastagaras/Halu-OAS-8B-Llama3 : focus on storytelling
23
 
24
- Quantified model files:
 
 
25
 
 
26
  - [static GGUF quants c/o mradermacher](https://huggingface.co/mradermacher/Llama-3-Oasis-v1-OAS-8B-GGUF)
27
  - [weighted/imatrix GGUF quants c/o mradermacher](https://huggingface.co/mradermacher/Llama-3-Oasis-v1-OAS-8B-i1-GGUF)
28
  - [8bpw exl2 quant](https://huggingface.co/grimjim/Llama-3-Oasis-v1-OAS-8B-8bpw_h8_exl2)
 
21
  - NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS : focus on roleplay
22
  - Hastagaras/Halu-OAS-8B-Llama3 : focus on storytelling
23
 
24
+ Tested with the following sampler settings:
25
+ - temperature 1-1.45
26
+ - minP 0.01-0.02
27
 
28
+ Quantified model files:
29
  - [static GGUF quants c/o mradermacher](https://huggingface.co/mradermacher/Llama-3-Oasis-v1-OAS-8B-GGUF)
30
  - [weighted/imatrix GGUF quants c/o mradermacher](https://huggingface.co/mradermacher/Llama-3-Oasis-v1-OAS-8B-i1-GGUF)
31
  - [8bpw exl2 quant](https://huggingface.co/grimjim/Llama-3-Oasis-v1-OAS-8B-8bpw_h8_exl2)