Run Code Llama with an API on Replicate. Code Llama can generate and discuss code. It's the best open-source model for things like debugging and code completion. • 7b https://
replicate.com/replicate/code
llama-7b
…
• 7b Python https://
replicate.com/replicate/code
llama-7b-python
…
• 13b
OPEN SOURCE
-
Code Llama API Available on Replicate with Multiple Models
By
–
-
RAG Closes Gap Between Open Source and API Providers
By
–
And using RAG could close the gap even further between the performance of open source alongside the API providers, particularly for companies that don’t want to hand over control to a provider and are looking for a cheaper, faster, and perhaps more importantly, predictable tool.
-
Open Source AI Models Accessible Without Fine-Tuning Resources
By
–
It's a tantalizing prospect for companies that are exploring the use of open source models, but don't have the resources (personnel or financial) to fine-tune or pre-train a model. It works right out of the box without any significantly advanced technical requirements.
-
Pretraining Llama 2 with New Data: Tutorial and Approach
By
–
Instead of training from scratch, you could take the existing Llama 2 base model and pretrain it for a few more epochs on new data and see how it performs. I set up a tutorial here the other day (you may want to swap the dataset depending on your usecase): https://
github.com/Lightning-AI/l
it-gpt/blob/main/tutorials/pretrain_redpajama.md
… -
Summer LLM Developments: Llama 2, CodeLlama, and GPT-4
By
–
Llama 2, CodeLlama, and leaked GPT-4 details. Here's my new write-up on the noteworthy developments around LLMs of this summer so far:
-
Implementing AI: accessibility and RLHF resources
By
–
Still a great list. Today I would add to dive as soon as possible in implementing something yourself since recent AI developments have become so accessible. We still need more good book/ressources on RLHF, maybe @natolambert or @_lewtun will fill this gap soon 🙂
-
Code Llama Outperforms Open-Source Solutions on HumanEval MBPP
By
–
We evaluated Code Llama against existing solutions on both HumanEval & MBPP.
– It performed better than open-source, code-specific LLMs & Llama 2.
– Code Llama 34B scored the highest vs other SOTA open solutions on MBPP — on par w/ ChatGPT. More info https://
bit.ly/45JiPwJ -
LIMA dataset recommendation for instruction finetuning with high-quality examples
By
–
Agreed! And there’s LIMA if you are looking for 1k high-quality examples for instruction finetuning:
-
Python ecosystem shifting to Rust over C++ for performance
By
–
Or more like a competitor to Rust since the Python ecosystem is moving to that instead of C++ (eg see polars and some others)? And for GPU & AI stuff a competitor to Triton/CUDA?
-
Code Llama Now Available in Hugging Face Playground
By
–
You can try Code Llama now in the Code Llama playground @huggingface space — it's also available in the Hugging Face ecosystem, starting with transformers version 4.33.