-
## Description
- [ ] Benchmark against other models to validate improvement
- [ ] It's possible we need to create a benchmark
-
Retrieval Augmented Generation is one of the top use cases for LLM. One of the critical challenges in RAG systems is properly referencing the sources of the retrieved documents within the LLM's respon…
-
-
Output:
```
Traceback (most recent call last):
File "", line 198, in _run_module_as_main
File "", line 88, in _run_code
File ".../x/InfLLM/inf_llm/chat.py", line 726, in
main(args)
…
-
稍微大一点的文件就报错
Error calling LLM API: 429 Client Error: Too Many Requests for url: https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro-latest:generateContent
-
### Feature request / 功能建议
how to use a local LLM to evaluate prediction quality? For example, Llama-3-70B-Instruct?
### Motivation / 动机
how to use a local LLM to evaluate prediction quality? For …
-
### Bug Description
When using AI nodes with local model, sometimes they take more than 5 mins to respond, which causes fetch to timeout (i looked through the code and past changes, and it seems to b…
-
i deifned this function to not use the LLM calls but it still give me this error:
Exception has occurred: AttributeError
'list' object has no attribute 'get_sample_type'
File "C:\Users\Amin\One…
-
### Description
Make LLM to program in Solidity, look for ways to collect data and then train it to create a model that is good enough to do its task, not to mention a small model that can run locall…
-
### Issue
We propose fine-grain speculative execution on metal. Specifically, we introduce a new type of parallelism where devices are used to pre-execute ops from speculative output.
- Speculative…