Picture

Tom Jobbins @TheBlokeAI

My Hugging Face repos: https://t.co/yh7J4DFGTc Discord server: https://t.co/5h6rGsGfBx Patreon: https://t.co/yfQwFggGtx patreon.com/TheBlokeAI UK Joined July 2010
  • Tweets
    336
  • Followers
    15K
  • Following
    227
  • Likes
    261
Tom Jobbins retweeted
theemozilla Profile Picture

emozilla @theemozilla

2 years ago

FYI to anyone using @MistralAI's Mixtral for long context tasks -- you can get even better performance by disabling sliding window attention (setting it to your max context length) config.sliding_window = 32768

TheBlokeAI Profile Picture

Tom Jobbins @TheBlokeAI

2 years ago

Transformers now supports Mixtral GPTQs and I've updated my READMEs accordingly. It was awesome working with @_marcsun and @younesbelkada of @huggingface on this! Credit to LaaZa for coding the AutoGPTQ quant and inference implementation which enabled me to get GPTQs out fast!

_marcsun Profile Picture

Marc Sun @_marcsun

2 years ago

Transformers now supports Mixtral GPTQs and I've updated my READMEs accordingly. It was awesome working with @_marcsun and @younesbelkada of @huggingface on this! Credit to LaaZa for coding the AutoGPTQ quant and inference implementation which enabled me to get GPTQs out fast!

Tom Jobbins retweeted
gordic_aleksa Profile Picture

Aleksa Gordić (水平问题) @gordic_aleksa

2 years ago

@TheBlokeAI joined me to share his work in the open-source AI space - don't miss it! happening right now server link: discord.gg/peBrCpheKE (see the general channel or events channel for google meet link)

Tom Jobbins retweeted
yb2698 Profile Picture

younes @yb2698

2 years ago

Blazing fast text generation using AWQ and fused modules! 🚀 Up to 3x speedup compared to native fp16 that you can use right now on any models supported by @TheBlokeAI Simply pass an `AwqConfig` with `do_fuse=True` to `from_pretrained` method! huggingface.co/docs/transform…

TheBlokeAI Profile Picture

Tom Jobbins @TheBlokeAI

2 years ago

It's been awesome to see Transformers getting support for more and more quantisation methods. And I've loved collaborating with @younesbelkada and @huggingface again! All my AWQ uploads now support Transformers. READMEs will update soon to show a Transformers Python example.

yb2698 Profile Picture

younes @yb2698

2 years ago

It's been awesome to see Transformers getting support for more and more quantisation methods. And I've loved collaborating with @younesbelkada and @huggingface again! All my AWQ uploads now support Transformers. READMEs will update soon to show a Transformers Python example.

Tom Jobbins retweeted
chirperai Profile Picture

Chirper @chirperai

2 years ago

Have you heard about Chirper worlds? 👀🌐

lazukars Profile Picture

Ryan Lazuka @lazukars

2 years ago

Have you heard about Chirper worlds? 👀🌐

Tom Jobbins retweeted
victormustar Profile Picture

Victor M @victormustar

2 years ago

🤔 Are you interested in a "Follow" feature on the Hugging Face Hub? ➡️ This will allow you to see new models/records/spaces from users you follow.

Tom Jobbins retweeted
julien_c Profile Picture

Julien Chaumond @julien_c

2 years ago

oh hello @TheBlokeAI I want to bookmark your 'Recent models' Collection on @huggingface 🔥 Well... you can now upvote Collections! and browse upvoted collections on your profile ❤️

TheBlokeAI Profile Picture

Tom Jobbins @TheBlokeAI

2 years ago

Thanks again to @latitudesh for the loan of a beast 8xH100 server this week. I uploaded over 550 new repos, maybe my busiest week yet! Quanting is really resource intensive. Needs not only fast GPUs, but many CPUs, lots of disk, and 🚀 network. A server that ✅ all is v. rare!

Tom Jobbins retweeted
lmarena_ai Profile Picture

lmarena.ai @lmarena_ai

2 years ago

🔥Excited to introduce LMSYS-Chat-1M, a large-scale dataset of 1M real-world conversations with 25 cutting-edge LLMs! This dataset, collected from chat.lmsys.org, offers insights into user interactions with LLMs and intriguing use cases. Link: huggingface.co/datasets/lmsys…

Tom Jobbins retweeted
yb2698 Profile Picture

younes @yb2698

2 years ago

New feature alert in the @huggingface ecosystem! Flash Attention 2 natively supported in huggingface transformers, supports training PEFT, and quantization (GPTQ, QLoRA, LLM.int8) First pip install flash attention and pass use_flash_attention_2=True when loading the model!

TheBlokeAI Profile Picture

Tom Jobbins @TheBlokeAI

2 years ago

This is fantastic! Git clone was already dead for HF as far as I was concerned - I had my own hf_upload.py and hf_download.py scripts (wrapping HfAPI) for fast, efficient transfers. But huggingface_hub v0.17 makes those redundant! I will be using this now. Awesome stuff,🤗

Wauplin Profile Picture

Wauplin @Wauplin

2 years ago

This is fantastic! Git clone was already dead for HF as far as I was concerned - I had my own hf_upload.py and hf_download.py scripts (wrapping HfAPI) for fast, efficient transfers. But huggingface_hub v0.17 makes those redundant! I will be using this now. Awesome stuff,🤗

Tom Jobbins retweeted
kramp Profile Picture

Bertrand Chevrier @kramp

2 years ago

This new filter 🔎 on @huggingface user's profile is very helpful, especially to check if @TheBlokeAI has quantized and released the last trending models 😁

Tom Jobbins retweeted
ggerganov Profile Picture

Georgi Gerganov @ggerganov

2 years ago

Casually running a 180B parameter LLM on M2 Ultra

Tom Jobbins retweeted
officialelinas Profile Picture

Elinas @officialelinas

2 years ago

Chronos 70B v2 release! Thanks to Pygmalion for generously providing the compute and @TheBlokeAI for quantizing the model. As usual, the model optimized for chat, roleplay, storywriting, and now includes vastly improved reasoning skills. huggingface.co/elinas/chronos…

TheBlokeAI Profile Picture

Tom Jobbins @TheBlokeAI

2 years ago

Just released by @pygmalionai : Pygmalion 2, the sequel to one of the most popular models ever! And Mythalion, a new Gryphe merge! huggingface.co/TheBloke/Pygma… huggingface.co/TheBloke/Pygma… huggingface.co/TheBloke/Pygma… huggingface.co/TheBloke/Pygma… huggingface.co/TheBloke/Mytha… huggingface.co/TheBloke/Mytha…

TheBlokeAI Profile Picture

Tom Jobbins @TheBlokeAI

2 years ago

Meta's CodeLlama is here! ai.meta.com/blog/code-llam… 7B, 7B-Instruct, 7B-Python, 13B, 13B-Instruct, 13B-Python, 34B, 34B-Instruct, 34B-Python First time we've seen the 34B model I've got a couple of fp16s up: huggingface.co/TheBloke/CodeL… huggingface.co/TheBloke/CodeL… More coming soon obvs

TheBlokeAI Profile Picture

Tom Jobbins @TheBlokeAI

2 years ago

Transformers 4.32.0 now supports GPTQ models natively! Over the last couple of days I have updated 296 of my GPTQ repos to provide automatic support for this. It's awesome you can now load a GPTQ model directly in Transformers with only two lines of code!

_marcsun Profile Picture

Marc Sun @_marcsun

2 years ago

Transformers 4.32.0 now supports GPTQ models natively! Over the last couple of days I have updated 296 of my GPTQ repos to provide automatic support for this. It's awesome you can now load a GPTQ model directly in Transformers with only two lines of code!

Trends for United States

#SmackDown
143 B posts
Chiefs
149 B posts
Mahomes
46,2 B posts
Mahomes
46,2 B posts
AJ Lee
153 B posts
Herbert
19,4 B posts
#KCvsLAC
4.677 posts
Rich Eisen
3.016 posts
Keenan Allen
3.542 posts
Karol G
34,2 B posts
Worthy
50,3 B posts
Jawaan Taylor
2.060 posts
Butker
7.138 posts
Brazil
127 B posts
Quentin Johnston
3.280 posts
Tanner Scott
1.171 posts
Edwin Diaz
2.092 posts
Sami
33,1 B posts
Hampton
9.162 posts
Ryan Clark
11,5 B posts

You might like

We make AI models Dolphin and Samantha BTC 3ENBV6zdwyqieAXzZP2i3EjeZtVwEmAuo4 https://t.co/3ri2GbWU13 https://t.co/zH0F3pSLuq @dphnAI
Eric Hartford
@QuixiAI
17K Followers
Human. Backend dev https://t.co/CJYvkACyne
Jon Durbin
@jon_durbin
5K Followers
The only AI researcher they sent a missile for 🇮🇱 | Co-host @thursdai_pod • AI news every Thursday
Yam Peleg
@Yampeleg
38K Followers
We remove the barriers to state-of-the-art generative AI model development and make data + AI available to all.
Databricks Mosaic Res...
@DbrxMosaicAI
41K Followers
LMArena: Open Platform for Community-driven AI Benchmarking. Graduated from UC Berkeley / @lmsysorg. We’re hiring: https://t.co/1OkfLq2n0I
lmarena.ai
@lmarena_ai
92K Followers
24th at the Electrica puzzle challenge | https://t.co/baTQS2bdia
Georgi Gerganov
@ggerganov
52K Followers
Co-founder & CEO @HuggingFace 🤗, the open and collaborative platform for AI builders
clem 🤗
@ClementDelangue
155K Followers
The AI Accelerator Company https://t.co/vrD0aDIGDQ
Nous Research
@NousResearch
81K Followers
Run, manage, and scale AI workloads on any AI infrastructure. Open-source system to access & manage all AI compute (Kubernetes, 17+ clouds, or on-prem).
SkyPilot
@skypilot_org
4K Followers
We’ll help you make it like nobody’s business. Multimodal media generation and editing tools to get your idea to production. Self-deploy? 👍 Need a partner? 🤝
Stability AI
@StabilityAI
242K Followers
Code & LLMs
anton
@abacaj
47K Followers
Build AI agents over your documents Github: https://t.co/HC19j7vMwc Docs: https://t.co/QInqg2zksh LlamaCloud: https://t.co/yQGTiRSNvj
LlamaIndex 🦙
@llama_index
101K Followers
Looking for a cofounder
Aran Komatsuzaki
@arankomatsuzaki
143K Followers
@LangChainAI, previously @robusthq @kensho MLOps ∪ Generative AI ∪ sports analytics
Harrison Chase
@hwchase17
79K Followers
Creator of bitsandbytes.Research Scientist @allen_ai and incoming professor @CarnegieMellon. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.
Tim Dettmers
@Tim_Dettmers
38K Followers