Window AI

113 posts

Window AI banner
Window AI

Window AI

@windowai_io

Use your own AI models on the web

Katılım Nisan 2023
84 Takip Edilen498 Takipçiler
Window AI retweetledi
Alex Atallah
Alex Atallah@alexatallah·
Two records last week for @openrouter: - Record # of models added in one week (12) - Record # of tokens processed (52 billion)
Alex Atallah tweet media
OpenRouter@OpenRouter

Launching 3 new models, including a Llama 3 finetune (free for a limited time). Focusing on performance and dynamic routing this week. New Models 👇 - Soliloquy 8B, a Llama 3 roleplay finetune - Fimbulvetr 11B, a highly-acclaimed roleplay model based on Solar - Llama 3 8B Extended to 16k context. Might not last forever, depending on usage

English
2
5
52
9.6K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Ever wondered which apps are using an LLM? Now you can find out yourself with the new Apps tab. @NousResearch has the top Claude 3 Opus apps this week 👀
OpenRouter tweet media
English
2
13
98
27.2K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Just crossed 100 million completions 🪅 See live statistics about 85 LLMs, along with latency and throughput for different hosts. More on the way: openrouter.ai/rankings
English
3
1
23
1.2K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
2/4: 🧡 Mistral Medium, Small, and Tiny (all 32k context) We've added support for @MistralAI's API-based models! Mistral Medium is showing some promising results, comparable with flagship models from others. Now you can get: - USD prices, without currency conversion - Compatibility with OpenRouter credits - Credit-based rate limiting The Small model compares with Mixtral 8x7b. Check out the Medium model here: openrouter.ai/models/mistral…
English
1
2
1
577
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Lots of updates: new Mistral models, big price cuts, and more! 1/4: 🤑 Price Cuts - MythoMax 13B: 63% price cut, down to $0.00022/1k tokens - Remm Slerp: 80% price cut, down to $0.00022/1k tokens That's 4.55M tokens per dollar, and less than 1/4th the price of GPT3.5. Check out stats here: openrouter.ai/models/gryphe/…
English
5
4
24
3.4K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Just launched an update to our Mixtral 8x7b Instruct router (still free!), which makes it 11x faster than before with 8x the context length. We also made our avg routing time 75% faster by improving edge tokenization. More perf improvements coming soon! openrouter.ai/models/mistral… (The previous Primary had an attention issue, so it's been reduced to 4k context, h/t @alexsablay and @WolframRvnwlf)
OpenRouter tweet media
English
6
14
120
31.8K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Our principles: 1. LLM prices are racing to the bottom. Make sure you benefit. 2. Use a Standardized API across models & providers 3. The best models will be used the most. Evals are flawed. Power users will figure out the best models for each use case. openrouter.ai/docs
OpenRouter tweet media
English
4
8
72
9.7K
Window AI retweetledi
Alex Atallah
Alex Atallah@alexatallah·
Not only are AI models commodities — they’re also increasingly hosted by multiple providers, particularly open source models. This means that a market is emerging between sellers (model hosts) and buyers. What’s the best way to get market efficiency on this? In my view, a centralized orderbook really helps, like @openrouter. The sellers will eventually decentralize though, and zkml or optimistic validation (like @ritualnet or @bittensororg ) could be ways of doing that.
Abe Murray@abemurray

Non consensus view: AI is already a commodity. OpenAI was not as good as Google’s best internal stuff (I know, was there, worked with teams building Google’s stuff). But they shipped faster and better. No one is 10x better, and OSS models are following fast. The winner will win by traditional techniques - better UI, better distribution, better marketing, etc.

English
2
2
23
3.8K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
The OpenAI saga created a big week for open models... 8 billion tokens processed on OpenRouter across 2000+ apps & 52 chat models 🛫
OpenRouter tweet media
English
0
3
18
1.5K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Excited to open-source our LLM inference engine! Based on @modal_labs and vLLM, it supports YaRN and RoPE context extension, and provides fallback hosting for many of the 50+ models on OpenRouter. 👉 github.com/OpenRouterTeam…
English
3
32
164
31.5K
Window AI retweetledi
Alex Atallah
Alex Atallah@alexatallah·
"Not your weights, not your models" is the new "not your keys, not your crypto"
English
7
10
52
4.7K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Another record week for open-source models!
OpenRouter tweet media
English
1
3
13
2.4K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
All-in on frankenmerges 🧌 Should we make a bounty for new ones? Ping us in Discord if you're building one that works, and we'll feature it!
Alex Atallah@alexatallah

I've become a big fan of "frankenmerge" LLMs that combine weights of open-source models and (inexplicably) result in something better than the sum of the parts. Feels like a very underexplored area of ML. Examples: Toppy by @Undi95 is now top of the fastest growing models on @openrouter, above GPT-4 Turbo, and MythoMax (red bar) has outpaced everyone. Goliath 120b is also new this weekend. Here's a search to track them all: openrouter.ai/models?q=%23me…

English
0
1
4
1.1K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
.@teknium's OpenHermes 2 is now the fastest-growing model on OpenRouter, by tokens processed:
OpenRouter tweet media
English
2
5
85
8.1K
Window AI retweetledi
OpenRouter
OpenRouter@OpenRouter·
Announcing our first roleplay data bounty 🧙 Submit your favorite AI roleplay chat sessions and get a change to win credits usable with any model on OpenRouter (including OpenAI, Claude, etc): 🥇 First place: $300 🥈 Second place: $200 🥉 Third place: $100 4th and 5th place both get $50. We'll judge them based on totally arbitrary factors: how emotionally gripping / insightful it is, how creative the user is, and how creative the AI is. Group chat submissions encouraged. Rules: 1. Multiple submissions per person are allowed. 2. You must include the app you used (e.g. Character AI, SillyTavern, etc) and the model, if you used a bring-your-own-model UI like ST 3. If we believe a submission was doctored and not actually created by AI, it's disqualified. 4. Deadline to submit: Friday Nov 10. If we don't receive at least 10 good submissions by Thursday, it may be extended by one week. 5. To submit, send an email from your OpenRouter account's email address to "support {-at-} openrouter.ai"
English
1
5
17
5.1K

Keşfet

@openrouter @NousResearch @RWKV_AI @MistralAI @alexsablay @WolframRvnwlf @ritualnet @bittensororg