Update README.md
Browse files
README.md
CHANGED
@@ -67,6 +67,19 @@ Special thanks to the model creators at MLABONNE for making such a fantastic mod
|
|
67 |
|
68 |
[ https://huggingface.co/mlabonne/Daredevil-8B-abliterated ]
|
69 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
<h3> Sample Prompt and Model's Compared:</h3>
|
71 |
|
72 |
Prompt tested with "temp=0" to ensure compliance, 2048 context (model supports 8192 context / 8k), and "chat" template for LLAMA3.
|
|
|
67 |
|
68 |
[ https://huggingface.co/mlabonne/Daredevil-8B-abliterated ]
|
69 |
|
70 |
+
<B>Highest Quality Settings / Optimal Operation Guide / Parameters and Samplers</B>
|
71 |
+
|
72 |
+
This a "Class 1" model:
|
73 |
+
|
74 |
+
For all settings used for this model (including specifics for its "class"), including example generation(s) and for advanced settings guide (which many times addresses any model issue(s)), including methods to improve model performance for all use case(s) as well as chat, roleplay and other use case(s) please see:
|
75 |
+
|
76 |
+
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
|
77 |
+
|
78 |
+
You can see all parameters used for generation, in addition to advanced parameters and samplers to get the most out of this model here:
|
79 |
+
|
80 |
+
[ https://huggingface.co/DavidAU/Maximizing-Model-Performance-All-Quants-Types-And-Full-Precision-by-Samplers_Parameters ]
|
81 |
+
|
82 |
+
|
83 |
<h3> Sample Prompt and Model's Compared:</h3>
|
84 |
|
85 |
Prompt tested with "temp=0" to ensure compliance, 2048 context (model supports 8192 context / 8k), and "chat" template for LLAMA3.
|