Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ tags:
|
|
16 |
|
17 |
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6303ca537373aacccd85d8a7/LxO9j7OykuabKLYQHIodG.jpeg)
|
18 |
|
19 |
-
|
20 |
|
21 |
This is a 120b frankenmerge of [miqu-1-70b](https://huggingface.co/miqudev/miqu-1-70b) created by interleaving layers of [miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) with itself using [mergekit](https://github.com/cg123/mergekit).
|
22 |
|
@@ -34,8 +34,8 @@ See also: [🐺🐦⬛ LLM Prompt Format Comparison/Test: Mixtral 8x7B Instru
|
|
34 |
|
35 |
## Model Details
|
36 |
|
37 |
-
|
38 |
-
|
39 |
|
40 |
## Merge Details
|
41 |
|
@@ -81,15 +81,15 @@ slices:
|
|
81 |
|
82 |
## Credits & Special Thanks
|
83 |
|
84 |
-
|
85 |
-
|
86 |
-
|
87 |
-
|
88 |
-
|
89 |
- gguf quantization: [ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++](https://github.com/ggerganov/llama.cpp)
|
90 |
|
91 |
### Support
|
92 |
|
93 |
-
|
94 |
|
95 |
#### DISCLAIMER: THIS IS [BASED ON A LEAKED ASSET](https://huggingface.co/miqudev/miqu-1-70b/discussions/10) AND HAS NO LICENSE ASSOCIATED WITH IT. USE AT YOUR OWN RISK.
|
|
|
16 |
|
17 |
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6303ca537373aacccd85d8a7/LxO9j7OykuabKLYQHIodG.jpeg)
|
18 |
|
19 |
+
- HF FP16: [wolfram/miqu-1-120b](https://huggingface.co/wolfram/miqu-1-120b)
|
20 |
|
21 |
This is a 120b frankenmerge of [miqu-1-70b](https://huggingface.co/miqudev/miqu-1-70b) created by interleaving layers of [miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) with itself using [mergekit](https://github.com/cg123/mergekit).
|
22 |
|
|
|
34 |
|
35 |
## Model Details
|
36 |
|
37 |
+
- Max Context: 32764 tokens (kept the weird number from the original/base model)
|
38 |
+
- Layers: 140
|
39 |
|
40 |
## Merge Details
|
41 |
|
|
|
81 |
|
82 |
## Credits & Special Thanks
|
83 |
|
84 |
+
- original (unreleased) model: [mistralai (Mistral AI_)](https://huggingface.co/mistralai)
|
85 |
+
- leaked model: [miqudev/miqu-1-70b](https://huggingface.co/miqudev/miqu-1-70b)
|
86 |
+
- f16 model: [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)
|
87 |
+
- mergekit: [arcee-ai/mergekit: Tools for merging pretrained large language models.](https://github.com/arcee-ai/mergekit)
|
88 |
+
- mergekit_config.yml: [nsfwthrowitaway69/Venus-120b-v1.2](https://huggingface.co/nsfwthrowitaway69/Venus-120b-v1.2)
|
89 |
- gguf quantization: [ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++](https://github.com/ggerganov/llama.cpp)
|
90 |
|
91 |
### Support
|
92 |
|
93 |
+
- [My Ko-fi page](https://ko-fi.com/wolframravenwolf) if you'd like to tip me to say thanks or request specific models to be tested or merged with priority. Also consider supporting your favorite model creators, quantizers, or frontend/backend devs if you can afford to do so. They deserve it!
|
94 |
|
95 |
#### DISCLAIMER: THIS IS [BASED ON A LEAKED ASSET](https://huggingface.co/miqudev/miqu-1-70b/discussions/10) AND HAS NO LICENSE ASSOCIATED WITH IT. USE AT YOUR OWN RISK.
|