![Tom Jobbins(@TheBlokeAI) 's Twitter Profileg](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
Tom Jobbins
@TheBlokeAI
My Hugging Face repos: https://t.co/yh7J4DFGTc
Discord server: https://t.co/5h6rGsGfBx
Patreon: https://t.co/yfQwFggGtx
ID:161524644
https://www.patreon.com/TheBlokeAI 01-07-2010 02:27:07
336 Tweets
15,4K Followers
237 Following
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
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
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
![chansung(@algo_diver) 's Twitter Profile Photo chansung(@algo_diver) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1337734515033174020/gyVhyP0O_200x200.jpg)
Currently working on adding GPTQ mode in LLM Chatbot! This will give more options to many of you.
Thanks to Tom Jobbins, all models are already quantized in GPTQ, so just need to integrate them.
First, GPU mode will be added. I had some issues with CPU (index out of range)
![chansung (@algo_diver) on Twitter photo 2023-07-24 13:49:08 Currently working on adding GPTQ mode in LLM Chatbot! This will give more options to many of you. Thanks to @TheBlokeAI, all models are already quantized in GPTQ, so just need to integrate them. First, GPU mode will be added. I had some issues with CPU (index out of range) Currently working on adding GPTQ mode in LLM Chatbot! This will give more options to many of you. Thanks to @TheBlokeAI, all models are already quantized in GPTQ, so just need to integrate them. First, GPU mode will be added. I had some issues with CPU (index out of range)](https://pbs.twimg.com/media/F1zmZROakAA0UJw.jpg)
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
![Eric Hartford(@erhartford) 's Twitter Profile Photo Eric Hartford(@erhartford) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1656477802399682560/OkfWtt1x_200x200.jpg)
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
An exciting few days with Llama 2!
But here's an interesting model that's flown under the radar: Upstage's Llama 30B Instruct. Eval shows it beating 65B & 70B?
Trained on OpenOrca + more.
Original: huggingface.co/upstage/llama-…
huggingface.co/TheBloke/upsta…
huggingface.co/TheBloke/upsta…
![Tim Dettmers(@Tim_Dettmers) 's Twitter Profile Photo Tim Dettmers(@Tim_Dettmers) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1465151884310683652/v4G_57En_200x200.jpg)
![ausboss — e/acc(@Zanzibased) 's Twitter Profile Photo ausboss — e/acc(@Zanzibased) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1666663511974445056/vbO5S1ow_200x200.jpg)
I've created a KoboldAI API wrapper for @langchain now available in v0.0.231 😀It's compatible with koboldcpp too!
If you are not familiar with KoboldAI its a popular webui for running local models.
Here's a glimpse of it running smoothly in a notebook. 👀 #opensource
![ausboss — e/acc (@Zanzibased) on Twitter photo 2023-07-12 16:23:25 I've created a KoboldAI API wrapper for @langchain now available in v0.0.231 😀It's compatible with koboldcpp too! If you are not familiar with KoboldAI its a popular webui for running local models. Here's a glimpse of it running smoothly in a notebook. 👀 #opensource I've created a KoboldAI API wrapper for @langchain now available in v0.0.231 😀It's compatible with koboldcpp too! If you are not familiar with KoboldAI its a popular webui for running local models. Here's a glimpse of it running smoothly in a notebook. 👀 #opensource](https://pbs.twimg.com/media/F02XJXBWAAIYBAi.png)
![Wing Lian (caseus)(@winglian) 's Twitter Profile Photo Wing Lian (caseus)(@winglian) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/463700890742837248/XlT4uzr2_200x200.png)
OpenOrca 13B Preview1 is here! huggingface.co/Open-Orca/Open…
Collaboration with Alignment Lab AI and Teknium (e/λ) to clean the dataset and getting a SoTA model out. Thanks to Tom Jobbins for quantization.
HF Spaces available to kick the tires on this model at huggingface.co/spaces/openacc…
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
The first OpenOrca preview is out! 🚀
'[we] reproduce the dataset generated for Microsoft's Orca Paper. We have trained on less than 6% of our data.. to preview of what is possible..'
My quants:
huggingface.co/TheBloke/OpenO…
huggingface.co/TheBloke/OpenO…
Original:
huggingface.co/Open-Orca/Open…
![Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo Tom Jobbins(@TheBlokeAI) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1505153936/Don_t_Panic_square_200x200.jpg)
I have reached quantisation nirvana.. making 9 GPTQs at once!
This Latitude.sh server is a monster, and it is always hungry! 👹
![Georgi Gerganov(@ggerganov) 's Twitter Profile Photo Georgi Gerganov(@ggerganov) 's Twitter Profile Photo](https://pbs.twimg.com/profile_images/1654097134315098113/zCZD0wYz_200x200.jpg)
llama.cpp now supports distributed inference across multiple devices via MPI
This is possible thanks to Evan Miller's work. Looking for people to give this a try and attempt to run a 65B LLaMA on cluster of Raspberry Pis 🙃
github.com/ggerganov/llam…