Training Bixtral, which is expensive + slow so mistakes are costly. The run finally finished, but then we got a sigkill -9 error (I believe it's a memory issue). I thought I lost the model, but I went into the output directory anyway, and luckily, it was there.
CODE
-
Apple Silicon GPU Programming Requires Different Libraries and Approach
By
–
Apple silicon is a whole different thing but yes it also has a GPU, and the code can also be targeted to it in a similar way, but all of the libraries and details change (Metal instead of CUDA) so it’s a whole separate effort.
-
Debugging Systems: Adding Permanent Metrics and Logging
By
–
When debugging an opaque problem in a system, a nice strategy is to just focus on adding permanent (rather than temporary) metrics or logging to make the problem obvious. Often makes it easy to solve not just the specific issue but also a whole class of potential related issues.
-
llm.c Performance Optimization: Closing Gap with PyTorch
By
–
A few new CUDA hacker friends joined the effort and now llm.c is only 2X slower than PyTorch (fp32, forward pass) compared to 4 days ago, when it was at 4.2X slower The biggest improvements were:
– turn on TF32 (NVIDIA TensorFLoat-32) instead of FP32 for matmuls. This is a -
v1.6.5 release: GPT-4 Turbo, Gemini 1.5, Command-R support
By
–
Quick minor release v1.6.5, supporting: GPT 4-Turbo Gemini 1.5-pro-latest Cohere Command-R We'll be adding support for images/videos upload for Gemini, and function calling with Anthropic Claude3 soon! Back to building
-
Jina AI Open Source Repository Availability Question
By
–
The FAQ says the code is open source, but I couldn't find the repo under https://
github.com/jina-ai – is the repo not public yet? -
Creating Workflows Using Natural Language Only
By
–
We're making it possible to create these kind of workflows using only language! DM me if you'd like early access to @Lutra_AI
-
Devin AI Agent Report Questioned as Possible Prank
By
–
Given that it was working fine before and it doesn’t use WP, and that this appears to be a report, not automated, I am guessing prank/dislike of Devin
-
Devin Coding Agent: Overclaim Concerns but Genuine Advanced Capabilities
By
–
i do think @lulumeservey may want to damage control this one. it was an obvious overclaim that lost a lot of fidelity in the final message. but still does not diminish the core utility that devin provides in that it really is the most advanced coding agent ive ever seen. not
-
LLM as Ultimate Compiler: From Pseudocode to Execution
By
–
Fair 🙂 I love the idea of an LLM as the ultimate compiler. Humans only write something like Python code, but even then it's just the prompt to get the idea across. So it's more like psuedocode and doesn't even have to be valid Python. Actually I already do this once in a while