4. Chat with local coding Assistant using Llama-3 pic.twitter.com/cee31drHoE
— Shubham Saboo (@Saboo_Shubham_) 14 juin 2024
4. Chat with local coding Assistant using Llama-3
LLMS
-
Local Coding Assistant Using Llama-3 Chat
By
–
-
Ollama LLM Provider Setup in CodeGPT Extension
By
–
3. Select Ollama as the LLM Provider
— Shubham Saboo (@Saboo_Shubham_) 14 juin 2024
• Go to the CodeGPT extension and select Ollama as your AI model
• After selecting Ollama, you can then select the models installed automatically. pic.twitter.com/NLxBj1fdew3. Select Ollama as the LLM Provider • Go to the CodeGPT extension and select Ollama as your AI model
• After selecting Ollama, you can then select the models installed automatically. -
Install Ollama Desktop and Download Llama-3 Model
By
–
1. Install Ollama for your Desktop • Download & Install the @ollama desktop app
• Run the following command to download llama-3 instruct model -
Free Local AI Code Assistant Llama-3 VS Code
By
–
AI code assistant in VS code using Llama-3 running locally on your computer (100% free and without internet):
-
Predicting Frontier AI Models Downstream Capabilities Remains Elusive
By
–
Excited to feature @RylanSchaeffer
's latest paper "Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?" on alphaXiv this week. Leave questions for Rylan directly on top of his paper: https://
alphaxiv.org/pdf/2406.04391 -
Yi-1.5 Surpasses 70k Downloads and 300 Community Models
By
–
Yi-1.5 has received over 70k+ downloads in the past month, and over 300 models have been created so far We're thrilled to see such incredible adoption. A huge thanks to our fantastic community for making this possible. Let’s keep building together
-
Free $25 Credits to Fine-Tune Small Language Models
By
–
To help get you started, here's $25 free credits on the house. That's enough to fine-tune a handful of SLMs for your use case: https://
lnkd.in/g7jHUDVX. -
Predibase Enables Affordable LoRA Fine-Tuning with LoRAX Technology
By
–
And, with Predibase, fine-tuning LoRA adapters is affordable (~$8), easy (2 lines of code or 2 clicks) and delivers GPT-4 level performance. We also have the secret sauce: #LoRAX (
http://
loraexchange.ai), our open-source for serving 100s of small adapters on a single base model -
LM Studio UI comparison simplifies local AI model deployment
By
–
Both are pretty much the same but LM Studio has added UI so that helps.
-
Cross-Document Attention Leakage in Sequence Packing Solutions
By
–
This paper tries to solve a non-issue actually . Their claim is that when you do packing (they call it concat and chunk lol) you get cross document attention leakage. The truth is that if your infra is decent you'll have segmentation masks that prevent this from happening in