-
LLaMA-2-7B-32K
Model Description
LLaMA-2-7B-32K is an open-source, long context language model developed by Together, fine-tuned from Meta's original Llama-2 7B model. This model represents our ef…
-
UPDATE (08/09/2023):
We have done major performance overhaul in the past few months, and now I'm happy to share the latest results:
- SOTA performance on CUDA: https://github.com/mlc-ai/llm-perf-b…
-
# Introduction
The recent advances in Large Language Models (LLMs) have enabled developers to utilize natural language in their applications with better quality and ability. As ChatGPT has shown, t…
-
### System Info
LangChain==0.0.177
Python==3.10
### Who can help?
_No response_
### Information
- [ ] The official example notebooks/scripts
- [ ] My own modified scripts
### Related Components…
-
### Bug Description
When I ask the LLM to graph using seaborn, I get this error even though Seaborn is in the allowed imports.
RuntimeError: Execution of code containing references to private or d…
-
When feeding the map_reduce summarization chain with a single document, the doc is run through an unnecessary map step before running a combine prompt on it.
The combine prompt would imo be sufficie…
-
I'm getting nan values for training and validation loss with recent git versions of mlx and mlx_lm (see commit hashes below).
This is the configuration file I'm using:
```yaml
config.yaml:
mod…
-
### Issue you'd like to raise.
Hi,
Not sure if someone is facting this "issue" or is something wrong I'm doing.
So far .. I read, GPT 3.5 turbo and later should be used with "chat_models" instead…
-
Hi guys,
I'm trying build a map_reduce chain to handle the long document summarization. Per my understanding, a long document will be cut into several parts firstly and then query the summary in ma…
-
**_Would it be possible to add a memory using embeddings, so that .txt files or documents could be loaded, converted to .json embeddings and then referenced by the AI before responding to prompts? wou…