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

chore(model gallery): add intellect-1-instruct (#4356)

Browse Source 
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
Ettore Di Giacinto 2024-12-10 09:42:37 +01:00 committed by GitHub
parent 3aff87a5cf
commit 272763f625
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

@ -1,4 +1,29 @@
---
- &intellect1
name: "intellect-1-instruct"
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master"
icon: https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct/resolve/main/intellect-1-map.png
urls:
- https://huggingface.co/PrimeIntellect/INTELLECT-1-Instruct
- https://huggingface.co/bartowski/INTELLECT-1-Instruct-GGUF
tags:
- llm
- gguf
- gpu
- cpu
- intellect
license: apache-2.0
description: |
INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.
This is an instruct model. The base model associated with it is INTELLECT-1.
INTELLECT-1 was trained on up to 14 concurrent nodes distributed across 3 continents, with contributions from 30 independent community contributors providing compute. The training code utilizes the prime framework, a scalable distributed training framework designed for fault-tolerant, dynamically scaling, high-perfomance training on unreliable, globally distributed workers. The key abstraction that allows dynamic scaling is the ElasticDeviceMesh which manages dynamic global process groups for fault-tolerant communication across the internet and local process groups for communication within a node. The model was trained using the DiLoCo algorithms with 100 inner steps. The global all-reduce was done with custom int8 all-reduce kernels to reduce the communication payload required, greatly reducing the communication overhead by a factor 400x.
overrides:
parameters:
model: INTELLECT-1-Instruct-Q4_K_M.gguf
files:
- filename: INTELLECT-1-Instruct-Q4_K_M.gguf
sha256: 5df236fe570e5998d07fb3207788eac811ef3b77dd2a0ad04a2ef5c6361f3030
uri: huggingface://bartowski/INTELLECT-1-Instruct-GGUF/INTELLECT-1-Instruct-Q4_K_M.gguf
- &llama33
url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master"
icon: https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/aJJxKus1wP5N-euvHEUq7.png