ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-11 21:12:58 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

chore(model gallery): add nvidia_llama-3.1-8b-ultralong-1m-instruct (#5176)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-14 12:28:09 +02:00 committed by GitHub
parent bef22ab547
commit 21ae7b4cd4
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
gallery/index.yaml
View File

@ -8135,6 +8135,21 @@
- filename: Hamanasu-Magnum-4B.i1-Q4_K_M.gguf
sha256: 7eb6d1bfda7c0a5bf62de754323cf59f14ddd394550a5893b7bd086fd1906361
uri: huggingface://mradermacher/Hamanasu-Magnum-4B-i1-GGUF/Hamanasu-Magnum-4B.i1-Q4_K_M.gguf
- !!merge <<: *llama31
name: "nvidia_llama-3.1-8b-ultralong-1m-instruct"
icon: https://cdn-avatars.huggingface.co/v1/production/uploads/1613114437487-60262a8e0703121c822a80b6.png
urls:
- https://huggingface.co/nvidia/Llama-3.1-8B-UltraLong-1M-Instruct
- https://huggingface.co/bartowski/nvidia_Llama-3.1-8B-UltraLong-1M-Instruct-GGUF
description: |
We introduce UltraLong-8B, a series of ultra-long context language models designed to process extensive sequences of text (up to 1M, 2M, and 4M tokens) while maintaining competitive performance on standard benchmarks. Built on the Llama-3.1, UltraLong-8B leverages a systematic training recipe that combines efficient continued pretraining with instruction tuning to enhance long-context understanding and instruction-following capabilities. This approach enables our models to efficiently scale their context windows without sacrificing general performance.
overrides:
parameters:
model: nvidia_Llama-3.1-8B-UltraLong-1M-Instruct-Q4_K_M.gguf
files:
- filename: nvidia_Llama-3.1-8B-UltraLong-1M-Instruct-Q4_K_M.gguf
sha256: 22e59b0eff7fd7b77403027fb758f75ad41c78a4f56adc10ca39802c64fe97fa
uri: huggingface://bartowski/nvidia_Llama-3.1-8B-UltraLong-1M-Instruct-GGUF/nvidia_Llama-3.1-8B-UltraLong-1M-Instruct-Q4_K_M.gguf
- !!merge <<: *llama33
name: "llama-3.3-magicalgirl-2.5-i1"
icon: https://cdn-uploads.huggingface.co/production/uploads/633e85093a17ab61de8d9073/FGK0qBGmELj6DEUxbbrdR.png