FWIW I wasn’t able to reproduce, using http://
labs.perplexity.ai with codellama-70b-instruct. I guess it depends on some detail of system prompt / format. I got 10/10 success using both prompts from the replies here and my own.
CODE
-
Codellama-70b-instruct success rate, prompt variations
By
–
-
MLX Community Releases Quantized Code Llama Models
By
–
Just finished uploading 4 MLX models. Quantized Code Llama 7B and 13B, Python and Instruct! Link here https://
huggingface.co/mlx-community -
CodeLlama-70B-Instruct Now Available on Perplexity Labs API
By
–
CodeLlama-70B-Instruct is now on Perplexity Labs and PPLX-API. Take it for a spin on https://t.co/2yYQB9jln7 pic.twitter.com/r33knimyST
— Perplexity (@perplexity_ai) 30 janvier 2024CodeLlama-70B-Instruct is now on Perplexity Labs and PPLX-API. Take it for a spin on http://
labs.pplx.ai -
Alternative Speech Method Counters Harmful Narratives Online
By
–
Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse Lee et al.: https://
arxiv.org/abs/2401.14616 #ArtificialIntelligence #DeepLearning #MachineLearning -
CodeLlama 7B Python quantized to 4-bit on MLX
By
–
I've just quantized CodeLlama 7b Python to 4-bit with MLX, meaning you can now run this model super fast on Apple Silicon. Here's the link to the model! https://
huggingface.co/mlx-community/
CodeLlama-7b-Python-4bit-MLX
… By the end of the day, my goal is to add all the new models. The 13B one is almost done! -
LangChain Trace: Public Tracking Link
By
–
Trace: https://smith.langchain.com/public/52dcdcd4-0fac-456e-b32b-e93e1cda9a2d/r
… Template:
— -
Building RAG Chatbot with Langchain ColBERT and ChromaDB
By
–
Build a Streamlit Chatbot using Langchain, ColBERT, Ragatouille, and ChromaDB Great resource on how to use ColBERT + Ragatouille + @trychroma + mixtral-8x7b-instruct-v0.1 + our EnsembleRetriever s/o @aigeek__ for building! Code: https://
github.com/aigeek0x0/rag-
with-langchain-colbert-and-ragatouille
… -
Practical Deep Learning Workshop at Cornell Tech
By
–
I'm teaching a little workshop this semester at cornell tech called Practical Deep Learning! it's supposed to be an intro to training neural networks and debugging them, in a modern context this is the schedule for the course. will post content here: http://
jxmo.io/deep-learning-
workshop/
… -
Slack Agent Toolkit: Empowering AI Agents with Workspace Integration
By
–
Slack Agent Toolkit Productivity and communication apps like Slack are powerful tools. We can easily give Agents the ability read from or write to channels within a Slack workspace. To explore this for yourself, check out the Slack agent toolkit:
-
CodeLlama 70B Release: New Open Source LLM Drop
By
–
new CodeLlama 70B drop from @syhw and team.
Offline benchmarks look pretty good, but try it out and see for yourself!