mirror of
https://github.com/mudler/LocalAI.git
synced 2025-04-26 05:50:01 +00:00
chore(model gallery) add llama_3.3_70b_darkhorse-i1 (#5222)
chore(model gallery): add llama_3.3_70b_darkhorse-i1 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
parent
4bc4b1e8bc
commit
7fc37c5e29
@ -112,7 +112,7 @@
|
|||||||
model: google_gemma-3-4b-it-qat-Q4_0.gguf
|
model: google_gemma-3-4b-it-qat-Q4_0.gguf
|
||||||
files:
|
files:
|
||||||
- filename: google_gemma-3-4b-it-qat-Q4_0.gguf
|
- filename: google_gemma-3-4b-it-qat-Q4_0.gguf
|
||||||
sha256: 0231e2cba887f4c7834c39b34251e26b2eebbb71dfac0f7e6e2b2c2531c1a583
|
sha256: 0231e2cba887f4c7834c39b34251e26b2eebbb71dfac0f7e6e2b2c2531c1a583
|
||||||
uri: huggingface://bartowski/google_gemma-3-4b-it-qat-GGUF/google_gemma-3-4b-it-qat-Q4_0.gguf
|
uri: huggingface://bartowski/google_gemma-3-4b-it-qat-GGUF/google_gemma-3-4b-it-qat-Q4_0.gguf
|
||||||
- !!merge <<: *gemma3
|
- !!merge <<: *gemma3
|
||||||
name: "gemma-3-27b-it-qat"
|
name: "gemma-3-27b-it-qat"
|
||||||
@ -1598,6 +1598,29 @@
|
|||||||
- filename: deepcogito_cogito-v1-preview-llama-70B-Q4_K_M.gguf
|
- filename: deepcogito_cogito-v1-preview-llama-70B-Q4_K_M.gguf
|
||||||
sha256: d1deaf80c649e2a9446463cf5e1f7c026583647f46e3940d2b405a57cc685225
|
sha256: d1deaf80c649e2a9446463cf5e1f7c026583647f46e3940d2b405a57cc685225
|
||||||
uri: huggingface://bartowski/deepcogito_cogito-v1-preview-llama-70B-GGUF/deepcogito_cogito-v1-preview-llama-70B-Q4_K_M.gguf
|
uri: huggingface://bartowski/deepcogito_cogito-v1-preview-llama-70B-GGUF/deepcogito_cogito-v1-preview-llama-70B-Q4_K_M.gguf
|
||||||
|
- !!merge <<: *llama33
|
||||||
|
name: "llama_3.3_70b_darkhorse-i1"
|
||||||
|
urls:
|
||||||
|
- https://huggingface.co/Nexesenex/Llama_3.3_70b_DarkHorse
|
||||||
|
- https://huggingface.co/mradermacher/Llama_3.3_70b_DarkHorse-i1-GGUF
|
||||||
|
description: |
|
||||||
|
Dark coloration L3.3 merge, to be included in my merges. Can also be tried as a standalone to have a darker Llama Experience, but I didn't take the time.
|
||||||
|
Edit : I took the time, and it meets its purpose.
|
||||||
|
|
||||||
|
It's average on the basic metrics (smarts, perplexity), but it's not woke and unhinged indeed.
|
||||||
|
The model is not abliterated, though. It has refusals on the usual point-blank questions.
|
||||||
|
I will play with it more, because it has potential.
|
||||||
|
|
||||||
|
My note : 3/5 as a standalone. 4/5 as a merge brick.
|
||||||
|
|
||||||
|
Warning : this model can be brutal and vulgar, more than most of my previous merges.
|
||||||
|
overrides:
|
||||||
|
parameters:
|
||||||
|
model: Llama_3.3_70b_DarkHorse.i1-Q4_K_M.gguf
|
||||||
|
files:
|
||||||
|
- filename: Llama_3.3_70b_DarkHorse.i1-Q4_K_M.gguf
|
||||||
|
sha256: 413a0b9203326ea78fdbdcfd89a3e0475a18f0f73fee3a6bfe1327e7b48942e2
|
||||||
|
uri: huggingface://mradermacher/Llama_3.3_70b_DarkHorse-i1-GGUF/Llama_3.3_70b_DarkHorse.i1-Q4_K_M.gguf
|
||||||
- &rwkv
|
- &rwkv
|
||||||
url: "github:mudler/LocalAI/gallery/rwkv.yaml@master"
|
url: "github:mudler/LocalAI/gallery/rwkv.yaml@master"
|
||||||
name: "rwkv-6-world-7b"
|
name: "rwkv-6-world-7b"
|
||||||
|
Loading…
x
Reference in New Issue
Block a user