Update README.md
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ tags:
|
|
12 |
|
13 |
Presenting the FP16 files for Psyonic-Cetacean-20B! This is an experimental Llama2-based stack merge based on the models and recipe below:
|
14 |
|
15 |
-
- [KoboldAI/PsyFighter-2-13b](https://huggingface.co/KoboldAI/
|
16 |
- [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b)
|
17 |
|
18 |
```yaml
|
@@ -21,13 +21,13 @@ Presenting the FP16 files for Psyonic-Cetacean-20B! This is an experimental Llam
|
|
21 |
- model: Orca2flat
|
22 |
layer_range: [0, 16]
|
23 |
- sources:
|
24 |
-
- model:
|
25 |
layer_range: [8, 24]
|
26 |
- sources:
|
27 |
- model: Orca2flat
|
28 |
layer_range: [17, 32]
|
29 |
- sources:
|
30 |
-
- model:
|
31 |
layer_range: [25, 40]
|
32 |
merge_method: passthrough
|
33 |
dtype: float16
|
|
|
12 |
|
13 |
Presenting the FP16 files for Psyonic-Cetacean-20B! This is an experimental Llama2-based stack merge based on the models and recipe below:
|
14 |
|
15 |
+
- [KoboldAI/PsyFighter-2-13b](https://huggingface.co/KoboldAI/LLaMA2-13B-Psyfighter2-GGUF)
|
16 |
- [microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b)
|
17 |
|
18 |
```yaml
|
|
|
21 |
- model: Orca2flat
|
22 |
layer_range: [0, 16]
|
23 |
- sources:
|
24 |
+
- model: LLaMA2-13B-Psyfighter2 (FP16 not yet available)
|
25 |
layer_range: [8, 24]
|
26 |
- sources:
|
27 |
- model: Orca2flat
|
28 |
layer_range: [17, 32]
|
29 |
- sources:
|
30 |
+
- model: LLaMA2-13B-Psyfighter2 (FP16 not yet available)
|
31 |
layer_range: [25, 40]
|
32 |
merge_method: passthrough
|
33 |
dtype: float16
|