ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-04-19 08:36:26 +00:00
Code Issues Actions 15 Packages Projects Releases Wiki Activity

models(gallery): add opencoder-8b instruct and base (#4101)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-11-10 10:28:47 +01:00 committed by GitHub
parent f1e03bf474
commit 0586fe2d9c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
gallery/index.yaml
View File

@ -1,4 +1,42 @@
---
- &opencoder
name: "opencoder-8b-base"
icon: https://github.com/OpenCoder-llm/opencoder-llm.github.io/blob/main/static/images/opencoder_icon.jpg?raw=true
url: "github:mudler/LocalAI/gallery/codellama.yaml@master"
urls:
- https://huggingface.co/infly/OpenCoder-8B-Base
- https://huggingface.co/QuantFactory/OpenCoder-8B-Base-GGUF
tags:
- llm
- gguf
- gpu
- cpu
- code
license: inf
description: |
The model is a quantized version of infly/OpenCoder-8B-Base created using llama.cpp. It is part of the OpenCoder LLM family which includes 1.5B and 8B base and chat models, supporting both English and Chinese languages. The original OpenCoder model was pretrained on 2.5 trillion tokens composed of 90% raw code and 10% code-related web data, and supervised finetuned on over 4.5M high-quality SFT examples. It achieves high performance across multiple language model benchmarks and is one of the most comprehensively open-sourced models available.
overrides:
parameters:
model: OpenCoder-8B-Base.Q4_K_M.gguf
files:
- filename: OpenCoder-8B-Base.Q4_K_M.gguf
sha256: ed158a6f72a40cf4f3f4569f649b365f5851e93f03b56252af3906515fab94ec
uri: huggingface://QuantFactory/OpenCoder-8B-Base-GGUF/OpenCoder-8B-Base.Q4_K_M.gguf
- !!merge <<: *opencoder
url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master"
name: "opencoder-8b-instruct"
urls:
- https://huggingface.co/infly/OpenCoder-8B-Instruct
- https://huggingface.co/QuantFactory/OpenCoder-8B-Instruct-GGUF
description: |
The LLM model is QuantFactory/OpenCoder-8B-Instruct-GGUF, which is a quantized version of infly/OpenCoder-8B-Instruct. It is created using llama.cpp and supports both English and Chinese languages. The original model, infly/OpenCoder-8B-Instruct, is pretrained on 2.5 trillion tokens composed of 90% raw code and 10% code-related web data, and supervised finetuned on over 4.5M high-quality SFT examples. It achieves high performance across multiple language model benchmarks and is one of the leading open-source models for code.
overrides:
parameters:
model: OpenCoder-8B-Instruct.Q4_K_M.gguf
files:
- filename: OpenCoder-8B-Instruct.Q4_K_M.gguf
sha256: ae642656f127e339fcb9566e6039a73cc55d34e3bf59e067d58ad40742f49f00
uri: huggingface://QuantFactory/OpenCoder-8B-Instruct-GGUF/OpenCoder-8B-Instruct.Q4_K_M.gguf
- &granite3
name: "granite-3.0-1b-a400m-instruct"
urls: