ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-01-27 14:49:39 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

chore(model gallery): add fastllama-3.2-1b-instruct (#4493)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-12-25 11:47:11 +01:00 committed by GitHub
parent 1d630e4185
commit 816ae7a53a
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

@ -964,6 +964,21 @@
- filename: Llama-Chat-Summary-3.2-3B-Q4_K_M.gguf
sha256: ed1be20d2374aa6db9940923f41fa229bd7ebe13d41b1ff1ff18a6f87e99df79
uri: huggingface://bartowski/Llama-Chat-Summary-3.2-3B-GGUF/Llama-Chat-Summary-3.2-3B-Q4_K_M.gguf
- !!merge <<: *llama32
name: "fastllama-3.2-1b-instruct"
icon: https://huggingface.co/suayptalha/FastLlama-3.2-1B-Instruct/resolve/main/FastLlama.png
urls:
- https://huggingface.co/suayptalha/FastLlama-3.2-1B-Instruct
- https://huggingface.co/bartowski/FastLlama-3.2-1B-Instruct-GGUF
description: |
FastLlama is a highly optimized version of the Llama-3.2-1B-Instruct model. Designed for superior performance in constrained environments, it combines speed, compactness, and high accuracy. This version has been fine-tuned using the MetaMathQA-50k section of the HuggingFaceTB/smoltalk dataset to enhance its mathematical reasoning and problem-solving abilities.
overrides:
parameters:
model: FastLlama-3.2-1B-Instruct-Q4_K_M.gguf
files:
- filename: FastLlama-3.2-1B-Instruct-Q4_K_M.gguf
sha256: 3c0303e9560c441a9abdcd0e4c04c47e7f6b21277c1e8c00eed94fc656da0be9
uri: huggingface://bartowski/FastLlama-3.2-1B-Instruct-GGUF/FastLlama-3.2-1B-Instruct-Q4_K_M.gguf
- &qwen25
## Qwen2.5
name: "qwen2.5-14b-instruct"