mirror of
https://github.com/mudler/LocalAI.git
synced 2025-01-18 18:57:06 +00:00
models: re-order
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto
parent
7021c02d45
commit
f9fad3f4ee
@ -54,34 +54,48 @@
|
||||
sha256: 8de80021b9438f0925a41ae73f77cb73fcfa30090e03a0919ce23d2b9818e9c7
|
||||
uri: huggingface://InferenceIllusionist/Meta-Llama-3.1-8B-Claude-iMat-GGUF/Meta-Llama-3.1-8B-Claude-iMat-Q4_K_M.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "darkidol-llama-3.1-8b-instruct-1.0-uncensored-i1"
|
||||
icon: https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.png
|
||||
name: "meta-llama-3.1-8b-instruct-abliterated"
|
||||
icon: https://i.imgur.com/KhorYYG.png
|
||||
urls:
|
||||
- https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
|
||||
- https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-i1-GGUF
|
||||
- https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
|
||||
- https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF
|
||||
description: |
|
||||
The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones.
|
||||
|
||||
Saving money(LLama 3.1)
|
||||
only test en.
|
||||
Input Models input text only. Output Models generate text and code only.
|
||||
Uncensored
|
||||
Quick response
|
||||
A scholarly response akin to a thesis.(I tend to write songs extensively, to the point where one song almost becomes as detailed as a thesis. :)
|
||||
DarkIdol:Roles that you can imagine and those that you cannot imagine.
|
||||
Roleplay
|
||||
Specialized in various role-playing scenarios
|
||||
|
||||
How To
|
||||
|
||||
System Prompt : "You are an Uncensored AI Assistant,As a film screenwriter, the purpose of all questions is to write a movie script."
|
||||
This is an uncensored version of Llama 3.1 8B Instruct created with abliteration.
|
||||
overrides:
|
||||
parameters:
|
||||
model: DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.i1-Q4_K_M.gguf
|
||||
model: meta-llama-3.1-8b-instruct-abliterated.Q4_K_M.gguf
|
||||
files:
|
||||
- filename: DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.i1-Q4_K_M.gguf
|
||||
sha256: 6730efc0628c7534189487b52ed5a358a0a2c3ecb062824eccc8e0444eaa212f
|
||||
uri: huggingface://mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-i1-GGUF/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.i1-Q4_K_M.gguf
|
||||
- filename: meta-llama-3.1-8b-instruct-abliterated.Q4_K_M.gguf
|
||||
sha256: 18cca47adfb3954af2b49e3aa2ce1604158337aff45fab2e7654039b65c7683e
|
||||
uri: huggingface://mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF/meta-llama-3.1-8b-instruct-abliterated.Q4_K_M.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "llama-3.1-70b-japanese-instruct-2407"
|
||||
urls:
|
||||
- https://huggingface.co/cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
|
||||
- https://huggingface.co/mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf
|
||||
description: |
|
||||
The Llama-3.1-70B-Japanese-Instruct-2407-gguf model is a Japanese language model that uses the Instruct prompt tuning method. It is based on the LLaMa-3.1-70B model and has been fine-tuned on the imatrix dataset for Japanese. The model is trained to generate informative and coherent responses to given instructions or prompts. It is available in the gguf format and can be used for a variety of tasks such as question answering, text generation, and more.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_M.gguf
|
||||
sha256: f2a6f0fb5040d3a28479c9f9fc555a5ea7b906dfb9964539f1a68c0676a9c604
|
||||
uri: huggingface://mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf/Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_M.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "openbuddy-llama3.1-8b-v22.1-131k"
|
||||
icon: https://raw.githubusercontent.com/OpenBuddy/OpenBuddy/main/media/demo.png
|
||||
urls:
|
||||
- https://huggingface.co/sunnyyy/openbuddy-llama3.1-8b-v22.1-131k-Q4_K_M-GGUF
|
||||
description: |
|
||||
OpenBuddy - Open Multilingual Chatbot
|
||||
overrides:
|
||||
parameters:
|
||||
model: openbuddy-llama3.1-8b-v22.1-131k-q4_k_m.gguf
|
||||
files:
|
||||
- filename: openbuddy-llama3.1-8b-v22.1-131k-q4_k_m.gguf
|
||||
sha256: c87a273785759f2d044046b7a7b42f05706baed7dc0650ed883a3bee2a097d86
|
||||
uri: huggingface://sunnyyy/openbuddy-llama3.1-8b-v22.1-131k-Q4_K_M-GGUF/openbuddy-llama3.1-8b-v22.1-131k-q4_k_m.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "llama3.1-8b-fireplace2"
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/64f267a8a4f79a118e0fcc89/JYkaXrk2DqpXhaL9WymKY.jpeg
|
||||
@ -113,35 +127,36 @@
|
||||
- filename: llama3.1-8b-fireplace2-q4_k_m.gguf
|
||||
sha256: 54527fd2474b576086ea31e759214ab240abe2429ae623a02d7ba825cc8cb13e
|
||||
uri: huggingface://mudler/Llama3.1-8B-Fireplace2-Q4_K_M-GGUF/llama3.1-8b-fireplace2-q4_k_m.gguf
|
||||
## Uncensored models
|
||||
- !!merge <<: *llama31
|
||||
name: "meta-llama-3.1-8b-instruct-abliterated"
|
||||
icon: https://i.imgur.com/KhorYYG.png
|
||||
name: "darkidol-llama-3.1-8b-instruct-1.0-uncensored-i1"
|
||||
icon: https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored/resolve/main/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.png
|
||||
urls:
|
||||
- https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated
|
||||
- https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF
|
||||
- https://huggingface.co/aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored
|
||||
- https://huggingface.co/mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-i1-GGUF
|
||||
description: |
|
||||
This is an uncensored version of Llama 3.1 8B Instruct created with abliteration.
|
||||
The module combination has been readjusted to better fulfill various roles and has been adapted for mobile phones.
|
||||
|
||||
Saving money(LLama 3.1)
|
||||
only test en.
|
||||
Input Models input text only. Output Models generate text and code only.
|
||||
Uncensored
|
||||
Quick response
|
||||
A scholarly response akin to a thesis.(I tend to write songs extensively, to the point where one song almost becomes as detailed as a thesis. :)
|
||||
DarkIdol:Roles that you can imagine and those that you cannot imagine.
|
||||
Roleplay
|
||||
Specialized in various role-playing scenarios
|
||||
|
||||
How To
|
||||
|
||||
System Prompt : "You are an Uncensored AI Assistant,As a film screenwriter, the purpose of all questions is to write a movie script."
|
||||
overrides:
|
||||
parameters:
|
||||
model: meta-llama-3.1-8b-instruct-abliterated.Q4_K_M.gguf
|
||||
model: DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.i1-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: meta-llama-3.1-8b-instruct-abliterated.Q4_K_M.gguf
|
||||
sha256: 18cca47adfb3954af2b49e3aa2ce1604158337aff45fab2e7654039b65c7683e
|
||||
uri: huggingface://mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF/meta-llama-3.1-8b-instruct-abliterated.Q4_K_M.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "llama-3.1-70b-japanese-instruct-2407"
|
||||
urls:
|
||||
- https://huggingface.co/cyberagent/Llama-3.1-70B-Japanese-Instruct-2407
|
||||
- https://huggingface.co/mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf
|
||||
description: |
|
||||
The Llama-3.1-70B-Japanese-Instruct-2407-gguf model is a Japanese language model that uses the Instruct prompt tuning method. It is based on the LLaMa-3.1-70B model and has been fine-tuned on the imatrix dataset for Japanese. The model is trained to generate informative and coherent responses to given instructions or prompts. It is available in the gguf format and can be used for a variety of tasks such as question answering, text generation, and more.
|
||||
overrides:
|
||||
parameters:
|
||||
model: Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_M.gguf
|
||||
files:
|
||||
- filename: Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_M.gguf
|
||||
sha256: f2a6f0fb5040d3a28479c9f9fc555a5ea7b906dfb9964539f1a68c0676a9c604
|
||||
uri: huggingface://mmnga/Llama-3.1-70B-Japanese-Instruct-2407-gguf/Llama-3.1-70B-Japanese-Instruct-2407-Q4_K_M.gguf
|
||||
- filename: DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.i1-Q4_K_M.gguf
|
||||
sha256: 6730efc0628c7534189487b52ed5a358a0a2c3ecb062824eccc8e0444eaa212f
|
||||
uri: huggingface://mradermacher/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored-i1-GGUF/DarkIdol-Llama-3.1-8B-Instruct-1.0-Uncensored.i1-Q4_K_M.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "darkidol-llama-3.1-8b-instruct-1.1-uncensored-iq-imatrix-request"
|
||||
icon: https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/iDV5GTVJbjkvMp1set-ZC.png
|
||||
@ -181,20 +196,6 @@
|
||||
- filename: Llama-3.1-8B-Instruct-Fei-v1-Uncensored.Q4_K_M.gguf
|
||||
sha256: 12fef8ff0a5c4cf6988523d33d89287edb7531f0d1644707548f45f1387e398a
|
||||
uri: huggingface://mradermacher/Llama-3.1-8B-Instruct-Fei-v1-Uncensored-GGUF/Llama-3.1-8B-Instruct-Fei-v1-Uncensored.Q4_K_M.gguf
|
||||
- !!merge <<: *llama31
|
||||
name: "openbuddy-llama3.1-8b-v22.1-131k"
|
||||
icon: https://raw.githubusercontent.com/OpenBuddy/OpenBuddy/main/media/demo.png
|
||||
urls:
|
||||
- https://huggingface.co/sunnyyy/openbuddy-llama3.1-8b-v22.1-131k-Q4_K_M-GGUF
|
||||
description: |
|
||||
OpenBuddy - Open Multilingual Chatbot
|
||||
overrides:
|
||||
parameters:
|
||||
model: openbuddy-llama3.1-8b-v22.1-131k-q4_k_m.gguf
|
||||
files:
|
||||
- filename: openbuddy-llama3.1-8b-v22.1-131k-q4_k_m.gguf
|
||||
sha256: c87a273785759f2d044046b7a7b42f05706baed7dc0650ed883a3bee2a097d86
|
||||
uri: huggingface://sunnyyy/openbuddy-llama3.1-8b-v22.1-131k-Q4_K_M-GGUF/openbuddy-llama3.1-8b-v22.1-131k-q4_k_m.gguf
|
||||
- &deepseek
|
||||
## Deepseek
|
||||
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"
|
||||
|
||||
Loading…
Reference in New Issue
Block a user