models(gallery): add arcee-spark (#2665)

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-06-26 20:06:40 +02:00 committed by GitHub
parent 2b6a2c7dde
commit e8bc0a789b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -107,6 +107,26 @@
- filename: Einstein-v7-Qwen2-7B-Q4_K_M.gguf - filename: Einstein-v7-Qwen2-7B-Q4_K_M.gguf
sha256: 277b212ea65894723d2b86fb0f689fa5ecb54c9794f0fd2fb643655dc62812ce sha256: 277b212ea65894723d2b86fb0f689fa5ecb54c9794f0fd2fb643655dc62812ce
uri: huggingface://bartowski/Einstein-v7-Qwen2-7B-GGUF/Einstein-v7-Qwen2-7B-Q4_K_M.gguf uri: huggingface://bartowski/Einstein-v7-Qwen2-7B-GGUF/Einstein-v7-Qwen2-7B-Q4_K_M.gguf
- !!merge <<: *qwen2
name: "arcee-spark"
icon: https://i.ibb.co/80ssNWS/o-Vdk-Qx-ARNmzr-Pi1h-Efj-SA.webp
description: |
Arcee Spark is a powerful 7B parameter language model that punches well above its weight class. Initialized from Qwen2, this model underwent a sophisticated training process:
Fine-tuned on 1.8 million samples
Merged with Qwen2-7B-Instruct using Arcee's mergekit
Further refined using Direct Preference Optimization (DPO)
This meticulous process results in exceptional performance, with Arcee Spark achieving the highest score on MT-Bench for models of its size, outperforming even GPT-3.5 on many tasks.
urls:
- https://huggingface.co/arcee-ai/Arcee-Spark-GGUF
overrides:
parameters:
model: Arcee-Spark-Q4_K_M.gguf
files:
- filename: Arcee-Spark-Q4_K_M.gguf
sha256: 44123276d7845dc13f73ca4aa431dc4c931104eb7d2186f2a73d076fa0ee2330
uri: huggingface://arcee-ai/Arcee-Spark-GGUF/Arcee-Spark-Q4_K_M.gguf
- &mistral03 - &mistral03
## START Mistral ## START Mistral
url: "github:mudler/LocalAI/gallery/mistral-0.3.yaml@master" url: "github:mudler/LocalAI/gallery/mistral-0.3.yaml@master"