ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-24 06:46:39 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

models(gallery): add reflection-llama-3.1-70b (#3487)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-09-06 12:52:43 +02:00 committed by GitHub
parent 11c16f529e
commit 36d980e520
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
gallery/index.yaml
View File

@ -423,6 +423,22 @@
- filename: Hubble-4B-v1-Q4_K_M.gguf - filename: Hubble-4B-v1-Q4_K_M.gguf
uri: huggingface://TheDrummer/Hubble-4B-v1-GGUF/Hubble-4B-v1-Q4_K_M.gguf uri: huggingface://TheDrummer/Hubble-4B-v1-GGUF/Hubble-4B-v1-Q4_K_M.gguf
sha256: 0721294d0e861c6e6162a112fc7242e0c4b260c156137f4bcbb08667f1748080 sha256: 0721294d0e861c6e6162a112fc7242e0c4b260c156137f4bcbb08667f1748080
- !!merge <<: *llama31
name: "reflection-llama-3.1-70b"
urls:
- https://huggingface.co/leafspark/Reflection-Llama-3.1-70B-bf16
- https://huggingface.co/senseable/Reflection-Llama-3.1-70B-gguf
description: |
Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
The model was trained on synthetic data generated by Glaive. If you're training a model, Glaive is incredible — use them.
overrides:
parameters:
model: Reflection-Llama-3.1-70B-q4_k_m.gguf
files:
- filename: Reflection-Llama-3.1-70B-q4_k_m.gguf
sha256: 16064e07037883a750cfeae9a7be41143aa857dbac81c2e93c68e2f941dee7b2
uri: huggingface://senseable/Reflection-Llama-3.1-70B-gguf/Reflection-Llama-3.1-70B-q4_k_m.gguf
## Uncensored models ## Uncensored models
- !!merge <<: *llama31 - !!merge <<: *llama31
name: "humanish-roleplay-llama-3.1-8b-i1" name: "humanish-roleplay-llama-3.1-8b-i1"