We have released "EvoSDXL-JP," an image generation model constructed using the "Evolutionary Model Merging" proposed by Sakana AI. The constructed model supports Japanese and can generate images 10 times faster than conventional Japanese models. Blog → https://
sakana.ai/evosdxl-jp
OPEN SOURCE
-
Sakana AI Releases EvoSDXL-JP Image Generation Model
By
–
-
Meta-Llama-3-70B-Instruct Q4 Quantized Model Implementation
By
–
I used the Meta-Llama-3-70B-Instruct.Q4_0.llamafile (quantized at Q4) file from here:
-
Running Llama-3-70B-Instruct locally on M4 Mac
By
–
Pleased to report that the Llamafile release of Llama-3-70B-Instruct works on my 64GB M4 – I had to download the 37GB file, quit a whole bunch of apps to free up RAM, then chmod 755 it, run ./Meta-Llama-3-70B-Instruct.Q4_0.llamafile and visit it on port 8080 on localhost
-
Llama2 English Language Performance Comparison Analysis
By
–
It also has hiccups in English. Llama2 does not have these.
-
Llama 3 70B via Ollama: GPT-4 quality but degradation issues
By
–
ollama run llama3:70b It seems to run well and feels like GPT-4, with the added benefit that there’s no “limit replies as much as possible” system restriction. However it pukes itself pretty quickly and starts emitting garbage.
-
Llama-3 8B Model Impresses with Local Laptop Performance Potential
By
–
I'm spending the weekend playing with the smaller version of Llama-3 (8bn) that will run on most laptops. It is really impressive, and it makes me think that extremely powerful models will run locally in future.
-
AI Math Olympiad Competition: Gemma 2B KerasNLP Starter Notebook
By
–
Are you doing the AI Math Olympiad competition on Kaggle? Here's a notebook to get you started with Gemma 2B with KerasNLP:
-
LangSmith 101: Trace, Log, Test Evaluate AI Applications
By
–
LangSmith 101, Boost your Responsible AI with LangChain's Powerful framework A good introductory video in LangSmith Learn how to trace, log, test, and evaluate your applications! https://
youtube.com/watch?v=p03YrC
vLy9Y
… -
Groq Predicts Exciting Second Half of 2024 with Growth
By
–
The rest of 2024 is going to be a lot of fun as we keep building out more capacity, we see open source providing more models, and the dev community is hitting it's creative stride making amazing apps. We're not even halfway into the year and it's ⚡️⚡️⚡️ right now! https://t.co/UlXXTpGTzr pic.twitter.com/wYU6dr8IaF
— Groq Inc (@GroqInc) 21 avril 2024The rest of 2024 is going to be a lot of fun as we keep building out more capacity, we see open source providing more models, and the dev community is hitting it's creative stride making amazing apps. We're not even halfway into the year and it's right now!
-
Llama 3 Family: 8B and 70B Models Released with Strong Performance
By
–
1/ Llama 3 – a family of LLMs that include 8B and 70B pretrained and instruction-tuned models; Llama 3 8B outperforms Gemma 7B and Mistral 7B Instruct; Llama 3 70 broadly outperforms Gemini Pro 1.5 and Claude 3 Sonnet.https://t.co/xqDJy0f0Vs
— DAIR.AI (@dair_ai) 21 avril 20241/ Llama 3 – a family of LLMs that include 8B and 70B pretrained and instruction-tuned models; Llama 3 8B outperforms Gemma 7B and Mistral 7B Instruct; Llama 3 70 broadly outperforms Gemini Pro 1.5 and Claude 3 Sonnet.