Skip to content

Commit 7fc37c5

Browse files
authored
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 <[email protected]>
1 parent 4bc4b1e commit 7fc37c5

File tree

1 file changed

+24
-1
lines changed

1 file changed

+24
-1
lines changed

gallery/index.yaml

+24-1
Original file line numberDiff line numberDiff line change
@@ -112,7 +112,7 @@
112112
model: google_gemma-3-4b-it-qat-Q4_0.gguf
113113
files:
114114
- filename: google_gemma-3-4b-it-qat-Q4_0.gguf
115-
sha256: 0231e2cba887f4c7834c39b34251e26b2eebbb71dfac0f7e6e2b2c2531c1a583
115+
sha256: 0231e2cba887f4c7834c39b34251e26b2eebbb71dfac0f7e6e2b2c2531c1a583
116116
uri: huggingface://bartowski/google_gemma-3-4b-it-qat-GGUF/google_gemma-3-4b-it-qat-Q4_0.gguf
117117
- !!merge <<: *gemma3
118118
name: "gemma-3-27b-it-qat"
@@ -1598,6 +1598,29 @@
15981598
- filename: deepcogito_cogito-v1-preview-llama-70B-Q4_K_M.gguf
15991599
sha256: d1deaf80c649e2a9446463cf5e1f7c026583647f46e3940d2b405a57cc685225
16001600
uri: huggingface://bartowski/deepcogito_cogito-v1-preview-llama-70B-GGUF/deepcogito_cogito-v1-preview-llama-70B-Q4_K_M.gguf
1601+
- !!merge <<: *llama33
1602+
name: "llama_3.3_70b_darkhorse-i1"
1603+
urls:
1604+
- https://huggingface.co/Nexesenex/Llama_3.3_70b_DarkHorse
1605+
- https://huggingface.co/mradermacher/Llama_3.3_70b_DarkHorse-i1-GGUF
1606+
description: |
1607+
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.
1608+
Edit : I took the time, and it meets its purpose.
1609+
1610+
It's average on the basic metrics (smarts, perplexity), but it's not woke and unhinged indeed.
1611+
The model is not abliterated, though. It has refusals on the usual point-blank questions.
1612+
I will play with it more, because it has potential.
1613+
1614+
My note : 3/5 as a standalone. 4/5 as a merge brick.
1615+
1616+
Warning : this model can be brutal and vulgar, more than most of my previous merges.
1617+
overrides:
1618+
parameters:
1619+
model: Llama_3.3_70b_DarkHorse.i1-Q4_K_M.gguf
1620+
files:
1621+
- filename: Llama_3.3_70b_DarkHorse.i1-Q4_K_M.gguf
1622+
sha256: 413a0b9203326ea78fdbdcfd89a3e0475a18f0f73fee3a6bfe1327e7b48942e2
1623+
uri: huggingface://mradermacher/Llama_3.3_70b_DarkHorse-i1-GGUF/Llama_3.3_70b_DarkHorse.i1-Q4_K_M.gguf
16011624
- &rwkv
16021625
url: "github:mudler/LocalAI/gallery/rwkv.yaml@master"
16031626
name: "rwkv-6-world-7b"

0 commit comments

Comments
 (0)