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 watt-ai_watt-tool-70b (#5138)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2025-04-08 09:42:49 +02:00 committed by GitHub
parent 547d322b28
commit c09d227647
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 25 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
gallery/index.yaml
View File

@ -1466,6 +1466,31 @@
- filename: Forgotten-Abomination-70B-v5.0.Q4_K_M.gguf
sha256: a5f5e712e66b855f36ff45175f20c24441fa942ca8af47bd6f49107c6e0f025d
uri: huggingface://mradermacher/Forgotten-Abomination-70B-v5.0-GGUF/Forgotten-Abomination-70B-v5.0.Q4_K_M.gguf
- !!merge <<: *llama33
name: "watt-ai_watt-tool-70b"
urls:
- https://huggingface.co/watt-ai/watt-tool-70B
- https://huggingface.co/bartowski/watt-ai_watt-tool-70B-GGUF
description: |
watt-tool-70B is a fine-tuned language model based on LLaMa-3.3-70B-Instruct, optimized for tool usage and multi-turn dialogue. It achieves state-of-the-art performance on the Berkeley Function-Calling Leaderboard (BFCL).
Model Description
This model is specifically designed to excel at complex tool usage scenarios that require multi-turn interactions, making it ideal for empowering platforms like Lupan, an AI-powered workflow building tool. By leveraging a carefully curated and optimized dataset, watt-tool-70B demonstrates superior capabilities in understanding user requests, selecting appropriate tools, and effectively utilizing them across multiple turns of conversation.
Target Application: AI Workflow Building as in https://lupan.watt.chat/ and Coze.
Key Features
Enhanced Tool Usage: Fine-tuned for precise and efficient tool selection and execution.
Multi-Turn Dialogue: Optimized for maintaining context and effectively utilizing tools across multiple turns of conversation, enabling more complex task completion.
State-of-the-Art Performance: Achieves top performance on the BFCL, demonstrating its capabilities in function calling and tool usage.
Based on LLaMa-3.1-70B-Instruct: Inherits the strong language understanding and generation capabilities of the base model.
overrides:
parameters:
model: watt-ai_watt-tool-70B-Q4_K_M.gguf
files:
- filename: watt-ai_watt-tool-70B-Q4_K_M.gguf
sha256: 93806a5482b9e40e50ffca7a72abe3414d384749cc9e3d378eab5db8a8154b18
uri: huggingface://bartowski/watt-ai_watt-tool-70B-GGUF/watt-ai_watt-tool-70B-Q4_K_M.gguf
- &rwkv
url: "github:mudler/LocalAI/gallery/rwkv.yaml@master"
name: "rwkv-6-world-7b"