models(gallery): add llama3.1-claude (#3005)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-07-24 23:40:08 +02:00 committed by GitHub
parent 80ae919dbe
commit 4a69ef3052
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -39,6 +39,20 @@
- filename: Meta-Llama-3.1-70B-Instruct.Q4_K_M.gguf - filename: Meta-Llama-3.1-70B-Instruct.Q4_K_M.gguf
sha256: 3f16ab17da4521fe3ed7c5d7beed960d3fe7b5b64421ee9650aa53d6b649ccab sha256: 3f16ab17da4521fe3ed7c5d7beed960d3fe7b5b64421ee9650aa53d6b649ccab
uri: huggingface://MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF/Meta-Llama-3.1-70B-Instruct.Q4_K_M.gguf uri: huggingface://MaziyarPanahi/Meta-Llama-3.1-70B-Instruct-GGUF/Meta-Llama-3.1-70B-Instruct.Q4_K_M.gguf
- !!merge <<: *llama31
name: "meta-llama-3.1-8b-claude-imat"
urls:
- https://huggingface.co/Undi95/Meta-Llama-3.1-8B-Claude
- https://huggingface.co/InferenceIllusionist/Meta-Llama-3.1-8B-Claude-iMat-GGUF
description: |
Meta-Llama-3.1-8B-Claude-iMat-GGUF: Quantized from Meta-Llama-3.1-8B-Claude fp16. Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 88 chunks and n_ctx=512. Static fp16 will also be included in repo. For a brief rundown of iMatrix quant performance, please see this PR. All quants are verified working prior to uploading to repo for your safety and convenience.
overrides:
parameters:
model: Meta-Llama-3.1-8B-Claude-iMat-Q4_K_M.gguf
files:
- filename: Meta-Llama-3.1-8B-Claude-iMat-Q4_K_M.gguf
sha256: 8de80021b9438f0925a41ae73f77cb73fcfa30090e03a0919ce23d2b9818e9c7
uri: huggingface://InferenceIllusionist/Meta-Llama-3.1-8B-Claude-iMat-GGUF/Meta-Llama-3.1-8B-Claude-iMat-Q4_K_M.gguf
## Deepseek ## Deepseek
- &deepseek - &deepseek
url: "github:mudler/LocalAI/gallery/deepseek.yaml@master" url: "github:mudler/LocalAI/gallery/deepseek.yaml@master"