ExternalVendorCode/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2024-12-20 05:07:54 +00:00
Code Issues Actions 13 Packages Projects Releases Wiki Activity

models(gallery): add opencoder-1.5b instruct and base (#4102)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-11-10 10:32:12 +01:00 committed by GitHub
parent 0586fe2d9c
commit 068b90a6dc
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 28 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
gallery/index.yaml
View File

@ -37,6 +37,34 @@
- filename: OpenCoder-8B-Instruct.Q4_K_M.gguf - filename: OpenCoder-8B-Instruct.Q4_K_M.gguf
sha256: ae642656f127e339fcb9566e6039a73cc55d34e3bf59e067d58ad40742f49f00 sha256: ae642656f127e339fcb9566e6039a73cc55d34e3bf59e067d58ad40742f49f00
uri: huggingface://QuantFactory/OpenCoder-8B-Instruct-GGUF/OpenCoder-8B-Instruct.Q4_K_M.gguf uri: huggingface://QuantFactory/OpenCoder-8B-Instruct-GGUF/OpenCoder-8B-Instruct.Q4_K_M.gguf
- !!merge <<: *opencoder
name: "opencoder-1.5b-base"
urls:
- https://huggingface.co/infly/OpenCoder-1.5B-Base
- https://huggingface.co/QuantFactory/OpenCoder-1.5B-Base-GGUF
description: |
The model is a large language model with 1.5 billion parameters, trained on 2.5 trillion tokens of code-related data. It supports both English and Chinese languages and is part of the OpenCoder LLM family which also includes 8B base and chat models. The model achieves high performance across multiple language model benchmarks and is one of the most comprehensively open-sourced models available.
overrides:
parameters:
model: OpenCoder-1.5B-Base.Q4_K_M.gguf
files:
- filename: OpenCoder-1.5B-Base.Q4_K_M.gguf
sha256: fb69a2849971b69f3fa1e64a17d1e4d3e1d0d3733d43ae8645299d07ab855af5
uri: huggingface://QuantFactory/OpenCoder-1.5B-Base-GGUF/OpenCoder-1.5B-Base.Q4_K_M.gguf
- !!merge <<: *opencoder
name: "opencoder-1.5b-instruct"
url: "github:mudler/LocalAI/gallery/hermes-2-pro-mistral.yaml@master"
urls:
- https://huggingface.co/QuantFactory/OpenCoder-1.5B-Instruct-GGUF
description: |
The model is a quantized version of [infly/OpenCoder-1.5B-Instruct](https://huggingface.co/infly/OpenCoder-1.5B-Instruct) created using llama.cpp. The original model, infly/OpenCoder-1.5B-Instruct, is an open and reproducible code LLM family which includes 1.5B and 8B base and chat models, supporting both English and Chinese languages. The model 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, positioning it among the leading open-source models for code.
overrides:
parameters:
model: OpenCoder-1.5B-Instruct.Q4_K_M.gguf
files:
- filename: OpenCoder-1.5B-Instruct.Q4_K_M.gguf
sha256: a34128fac79e05a3a92c3fd2245cfce7c3876c60241ec2565c24e74b36f48d56
uri: huggingface://QuantFactory/OpenCoder-1.5B-Instruct-GGUF/OpenCoder-1.5B-Instruct.Q4_K_M.gguf
- &granite3 - &granite3
name: "granite-3.0-1b-a400m-instruct" name: "granite-3.0-1b-a400m-instruct"
urls: urls: