ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-18 20:27:57 +00:00
Code Issues Actions 12 Packages Projects Releases Wiki Activity

models(gallery): add qwen2.5-math-7b-instruct (#3609)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-09-20 11:18:49 +02:00 committed by GitHub
parent a2a63460e9
commit c15f506fd5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 18 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
gallery/index.yaml
View File

@ -22,6 +22,24 @@
- filename: Qwen2.5-14B-Instruct-Q4_K_M.gguf - filename: Qwen2.5-14B-Instruct-Q4_K_M.gguf
sha256: e47ad95dad6ff848b431053b375adb5d39321290ea2c638682577dafca87c008 sha256: e47ad95dad6ff848b431053b375adb5d39321290ea2c638682577dafca87c008
uri: huggingface://bartowski/Qwen2.5-14B-Instruct-GGUF/Qwen2.5-14B-Instruct-Q4_K_M.gguf uri: huggingface://bartowski/Qwen2.5-14B-Instruct-GGUF/Qwen2.5-14B-Instruct-Q4_K_M.gguf
- !!merge <<: *qwen25
name: "qwen2.5-math-7b-instruct"
urls:
- https://huggingface.co/bartowski/Qwen2.5-Math-7B-Instruct-GGUF
- https://huggingface.co/Qwen/Qwen2.5-Math-7B-Instruct
description: |
In August 2024, we released the first series of mathematical LLMs - Qwen2-Math - of our Qwen family. A month later, we have upgraded it and open-sourced Qwen2.5-Math series, including base models Qwen2.5-Math-1.5B/7B/72B, instruction-tuned models Qwen2.5-Math-1.5B/7B/72B-Instruct, and mathematical reward model Qwen2.5-Math-RM-72B.
Unlike Qwen2-Math series which only supports using Chain-of-Thught (CoT) to solve English math problems, Qwen2.5-Math series is expanded to support using both CoT and Tool-integrated Reasoning (TIR) to solve math problems in both Chinese and English. The Qwen2.5-Math series models have achieved significant performance improvements compared to the Qwen2-Math series models on the Chinese and English mathematics benchmarks with CoT.
The base models of Qwen2-Math are initialized with Qwen2-1.5B/7B/72B, and then pretrained on a meticulously designed Mathematics-specific Corpus. This corpus contains large-scale high-quality mathematical web texts, books, codes, exam questions, and mathematical pre-training data synthesized by Qwen2.
overrides:
parameters:
model: Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf
files:
- filename: Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf
sha256: 7e03cee8c65b9ebf9ca14ddb010aca27b6b18e6c70f2779e94e7451d9529c091
uri: huggingface://bartowski/Qwen2.5-Math-7B-Instruct-GGUF/Qwen2.5-Math-7B-Instruct-Q4_K_M.gguf
## SmolLM ## SmolLM
- &smollm - &smollm
url: "github:mudler/LocalAI/gallery/chatml.yaml@master" url: "github:mudler/LocalAI/gallery/chatml.yaml@master"