Axolotl Profile
Axolotl

@axolotl_ai

Followers
2K
Following
77
Media
10
Statuses
89

Axolotl is the premier open source LLM fine tuning framework. find us on discord https://t.co/wlcE2wlJa9

San Francisco, CA
Joined December 2023
Don't wanna be here? Send us removal request.
@axolotl_ai
Axolotl
17 days
DenseMixer:
@fengyao1909
Feng Yao
24 days
๐Ÿ˜ตโ€๐Ÿ’ซ Struggling with ๐Ÿ๐ข๐ง๐ž-๐ญ๐ฎ๐ง๐ข๐ง๐  ๐Œ๐จ๐„?. Meet ๐ƒ๐ž๐ง๐ฌ๐ž๐Œ๐ข๐ฑ๐ž๐ซ โ€” an MoE post-training method that offers more ๐ฉ๐ซ๐ž๐œ๐ข๐ฌ๐ž ๐ซ๐จ๐ฎ๐ญ๐ž๐ซ ๐ ๐ซ๐š๐๐ข๐ž๐ง๐ญ, making MoE ๐ž๐š๐ฌ๐ข๐ž๐ซ ๐ญ๐จ ๐ญ๐ซ๐š๐ข๐ง and ๐›๐ž๐ญ๐ญ๐ž๐ซ ๐ฉ๐ž๐ซ๐Ÿ๐จ๐ซ๐ฆ๐ข๐ง๐ !. Blog:
Tweet media one
0
0
1
@axolotl_ai
Axolotl
17 days
ALST:
@StasBekman
Stas Bekman
1 month
My first project at @Snowflake AI Research is complete! . I present to you Arctic Long Sequence Training (ALST) . Paper: Blog: ALST is a set of modular, open-source techniques that enable training on sequences up to 15 million
Tweet media one
0
1
2
@axolotl_ai
Axolotl
17 days
Axolotl v0.11.0 is out! We've included ALST's TiledMLP for increased long sequence length training as well as support for Devstral, DenseMixer (MoE performance), and support for the most recent releases of transformers 4.53.1, accelerate 1.8.1, and FlashAttention2.
3
5
14
@axolotl_ai
Axolotl
1 month
RT @RedHat_AI: ๐Ÿšจ Introducing the Axolotl-LLM Compressor integration, designed to make fine-tuning sparse models easier and more efficient tโ€ฆ.
0
14
0
@axolotl_ai
Axolotl
1 month
@RedHat_AI Read about the full workflow here:
Tweet card summary image
developers.redhat.com
A sparse summary
0
0
3
@axolotl_ai
Axolotl
1 month
Are inference costs for serving your fine-tuned models on your mind? With @axolotl_ai and @RedHat_AI's LLM-Compressor you can now fine-tune sparsified LLMs for up to:.- ๐ŸŽฏ >99% accuracy recovery.- ๐Ÿ” 5x smaller models.- ๐Ÿš€ 3x faster inference.
1
5
13
@axolotl_ai
Axolotl
1 month
RT @capetorch: Training qwe3 with qwen2.5 template works just fine. Way easier to make everything work, and just one line change in @axolotโ€ฆ.
0
1
0
@axolotl_ai
Axolotl
1 month
RT @gokoyeb: Looking to fine-tune models?. Meet @axolotl_ai ๐Ÿ’š an open-source tool that simplifies the entire fine-tuning pipeline. Learn hoโ€ฆ.
Tweet card summary image
koyeb.com
Learn how to fine-tune Llama 3 using Axolotl. This hands-on guide covers setup, configuration with YAML, LoRA/QLoRA methods, and fine-tuning with serverless GPUs.
0
3
0
@axolotl_ai
Axolotl
2 months
Hacker house was in full force last week for @aiDotEngineer with events with @runpod_io plus collab with @googlecloud. sailing with team + @capetorch visits @SHACK15sf . โ›ต๏ธ๐Ÿ”ฅ ๐Ÿ˜Š.
@DesireeCachette
Dรฉsirรฉe Cachette
2 months
Wrapping up great week building and bonding with @axolotl_ai
Tweet media one
Tweet media two
1
1
5
@axolotl_ai
Axolotl
2 months
RT @sophiamyang: @MistralAI @64 Magistral Small is an open-weight model, and is available for self-deployment under the Apache 2.0 license.โ€ฆ.
0
2
0
@axolotl_ai
Axolotl
2 months
RT @winglian: Using @googlecloud ๐Ÿค @axolotl_ai can help you streamline your large Multimodal finetuning workflows.
Tweet media one
0
3
0
@axolotl_ai
Axolotl
2 months
Deploy Axolotl with @googlecloud for your production workloads with simple configuration based orchestration.
@winglian
Wing Lian (caseus)
2 months
Using @googlecloud ๐Ÿค @axolotl_ai can help you streamline your large Multimodal finetuning workflows.
Tweet media one
0
5
8
@axolotl_ai
Axolotl
2 months
RT @runpod_io: Spot the runpod truck in sf and get $250 in gpu credits. Snap a pic + tag @runpod_io and we'll send you a credit code ๐Ÿค. Hinโ€ฆ.
0
3
0
@axolotl_ai
Axolotl
2 months
. 7. devs away from 200 @github contributors ๐Ÿ˜‡
Tweet media one
1
0
6
@axolotl_ai
Axolotl
2 months
RT @iScienceLuvr: Model Merging in Pre-training of Large Language Models. "We present the Pre-trained Model Averaging (PMA) strategy, a novโ€ฆ.
0
83
0
@axolotl_ai
Axolotl
2 months
RT @winglian: Come join us on June 8th at Shack15 to accelerate AI on AMD, ARM, and other accelerators!.
0
4
0
@axolotl_ai
Axolotl
2 months
Current status: v0.9.2
Tweet media one
0
0
1
@axolotl_ai
Axolotl
2 months
Come hack with us in SF June 8th.
0
1
0