GITHUB HUGGING FACE MODELSCOPE DISCORD We release Qwen3 Embedding series, a new proprietary model of the Qwen model family. These models are specifically designed for text…
Merge pull request #55 from qscqesze/docs/upgrade_docker Update vLLM deployment doc to use Docker image for vLLM v0.8.3
"In projecting language back as the model for thought, we lose sight of the tacit embodied understanding that undergirds our intelligence." –Terry WinogradThe recent successes of…
Recsys & search are converging with LLMs via semantic IDs, data augmentation, and unified foundation models.
Secure Minions is a secure protocol built by Stanford's Hazy Research lab to allow encrypted local-remote communication.
LoRA Fine-Tune Support Now Live on GroqCloud
Using Product Key Memories to encode sparse coder features
Ollama now has the ability to enable or disable thinking. This gives users the flexibility to choose the model’s thinking behavior for different applications and use…
From Speed to Scale: How Groq Is Optimized for MoE & Other Large Models
Probably the first product Thinky will build is a full panel of dials that researchers can use to physically adjust all the hparams during training. We…
Merge pull request #259 from TianQi-777/patch-3 Update README.md
What makes a good leader? What do good leaders do? And commando, soldier, and police leadership.
Giving your models more time to think before prediction, like via smart decoding, chain-of-thoughts reasoning, latent thoughts, etc, turns out to be quite effective for unblocking…
How to Build Your Own AI Research Agent with One Groq API Call
When a new dataset comes out, I get excited and check it out and then only realize that this is another meta-mixed dataset combining a collections…
Merge pull request #51 from qscqesze/fix_guide Correct the spelling error in the ReadMe file: change guild to guide.
Correct the spelling error in the ReadMe file: change guild to guide. Signed-off-by: qingjun
Why build LLMs from scratch? It's probably the best and most efficient way to learn how LLMs really work. Plus, many readers have told me they…
Merge pull request #47 from qscqesze/vl_guild Update the vllm_deployment_guild_cn.md and vllm_deployment_guild.md
fix up readme.md Signed-off-by: qingjun
Update the vllm_deployment_guild_cn.md and vllm_deployment_guild.md files to explicitly specify the model names as MiniMax-Text-01 and MiniMax-VL-01, and revise the related descriptions to improve the accuracy and…
Benchmark results for Qwen3 models using the Aider polyglot coding benchmark.
The $6.32 benchmark cost reported for Gemini 2.5 Pro Preview 03-25 was incorrect.
更新 vllm_deployment_guild_cn.md 和 vllm_deployment_guild.md 文件，修改模型名称为 MiniMax 系列，新增 MiniMax-VL-01 模型获取说明及相关命令。 Signed-off-by: qingjun