ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-03-25 13:27:43 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

chore(model gallery): add sao10k_llama-3.3-70b-vulpecula-r1 (#5050)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-03-21 09:08:55 +01:00 committed by GitHub
parent 2c129843a7
commit 31a21d4a2c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 22 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
gallery/index.yaml
View File

@ -1132,6 +1132,28 @@
- filename: nvidia_Llama-3_3-Nemotron-Super-49B-v1-Q4_K_M.gguf
sha256: d3fc12f4480cad5060f183d6c186ca47d800509224632bb22e15791711950524
uri: huggingface://bartowski/nvidia_Llama-3_3-Nemotron-Super-49B-v1-GGUF/nvidia_Llama-3_3-Nemotron-Super-49B-v1-Q4_K_M.gguf
- !!merge <<: *llama33
name: "sao10k_llama-3.3-70b-vulpecula-r1"
icon: https://huggingface.co/Sao10K/Llama-3.3-70B-Vulpecula-r1/resolve/main/senkooo.jpg
urls:
- https://huggingface.co/Sao10K/Llama-3.3-70B-Vulpecula-r1
- https://huggingface.co/bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF
description: |
🌟 A thinking-based model inspired by Deepseek-R1, trained through both SFT and a little bit of RL on creative writing data.
🧠 Prefill, or begin assistant replies with <think>\n to activate thinking mode, or not. It works well without thinking too.
🚀 Improved Steerability, instruct-roleplay and creative control over base model.
👾 Semi-synthetic Chat/Roleplaying datasets that has been re-made, cleaned and filtered for repetition, quality and output.
🎭 Human-based Natural Chat / Roleplaying datasets cleaned, filtered and checked for quality.
📝 Diverse Instruct dataset from a few different LLMs, cleaned and filtered for refusals and quality.
💭 Reasoning Traces taken from Deepseek-R1 for Instruct, Chat & Creative Tasks, filtered and cleaned for quality.
█▓▒ Toxic / Decensorship data was not needed for our purposes, the model is unrestricted enough as is.
overrides:
parameters:
model: Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf
files:
- filename: Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf
sha256: 817073c85286c25a9373f330aad32b503e6c13d626a3fbee926d96a7ab866845
uri: huggingface://bartowski/Sao10K_Llama-3.3-70B-Vulpecula-r1-GGUF/Sao10K_Llama-3.3-70B-Vulpecula-r1-Q4_K_M.gguf
- &rwkv
url: "github:mudler/LocalAI/gallery/rwkv.yaml@master"
name: "rwkv-6-world-7b"