New release of ttok (version 0.3) adds a "–allow-special" option that fixes that: https://
github.com/simonw/ttok/re
leases/tag/0.3
…
CODE
-
ttok 0.3 releases new allow-special option for tokenization
By
–
-
OpenAI tiktoken library rejects special tokens by default
By
–
TIL the OpenAI tikoken library rejects text that includes special tokens by default, which affects my own "ttok" CLI tool – it raises an error if you call it like this: ttok '' –encode
-
Escaping Implementation Guidance Security Best Practices
By
–
That's what I'm looking for here – guidance on how that kind of escaping should be implemented, ideally backed up by demonstrations of what goes wrong if you don't and how the proposed escaping mechanism prevents those issues
-
Fine-tuning models for knowledge addition and RAG applications
By
–
That's not quite what I'm looking for – I believe that fine-tuning can work for things like adjusting the tone of the model's responses, the thing I'm seeking evidence for is fine-tuning in order to add additional knowledge to a model such that it can be used for RAG-style Q&A
-
Cursor’s OpenAI Technology: RAG or GPT-3.5 Fine-tuning?
By
–
The smallprint says "Cursor uses artificial intelligence technology provided by OpenAI, LLC" – so presumably it's RAG? Or did they do a fine-tune of GPT-3.5?
-
Targeted AI Systems Answering Documentation Questions Efficiently
By
–
By "targeted" I mean something like "answer questions about this documentation" – the kind of thing you might alternatively use RAG for
-
Lamini Tutorial Announcement: Creating AI Applications
By
–
Congrats Sharon, Lamini is super cool. Planning to create a tutorial on that super soon.
-
Workshop Replay: Fine-tune and Serve LLMs Rivaling GPT-4
By
–
ICYMI: Earlier this week, we held a virtual hands-on #workshop for 250+ developers on how to efficiently #finetune and serve your own LLMs that rival #GPT4. Here's the replay for anyone interesting in trying it out:
-
LLMs in Space: Hardening llm.c to NASA Safety Standards
By
–
Clearly LLMs must one day run in Space Step 1 we harden llm.c to pass the NASA code standards and style guides, certifying that the code is super safe, safe enough to run in Space. https://
en.wikipedia.org/wiki/The_Power
_of_10:_Rules_for_Developing_Safety-Critical_Code
… (see the linked PDF)
LLM training/inference in principle should be super -
Llama3 Local RAG Implementation Code Guide
By
–
Here's the code, assuming you know how to pull and run the models from Ollama. But still, if you face any issues please file a GitHub issue and I can take a look. https://
github.com/Shubhamsaboo/a
wesome-llm-apps/tree/main/llama3_local_rag
…