-
```
[general]
parser_type = "multi_stage"
ref_metadata_method = "none"
[model]
model_name = "mistralai/mistral-7b-instruct"
temperature = 0.6
[ontology]
versions = ["v0"]
notion_db_id =…
-
### Describe the bug
it seems code is not compatible with llama response
### Steps to reproduce
Error logs
```zsh
2024-11-18 12:26:45.377 | DEBUG | ai_hawk.llm.llm_manager:parse_llmresult:38…
-
### Please check that this issue hasn't been reported before.
- [X] I searched previous [Bug Reports](https://github.com/OpenAccess-AI-Collective/axolotl/labels/bug) didn't find any similar reports.
…
-
I have tried to install it on Ubuntu with ollama:mistral and followed the process as per the installation manual. I am getting the following error with unsafe_settings. Any ideas?
ubuntu@ip-172-31-…
-
They have implemented LongRope patch for llama and mistral. Is it possible to port same into ligGPT ?
https://github.com/datamllab/LongLM/tree/master
-
## Context:
The ability to use the Mistral-7B model on an M1 chip would reduce the need for remote compute resources. Based on work completed in #15, Mistral could be used effectively with Google C…
-
I'm trying to load Mistral 7B 32K. I've chunked the 4.3GB model and uploaded it to huggingface.
When the download is seemingly complete, there is a warning about being out of memory:
It's a …
-
### Issue: TypeError when initializing `task_type` using `unsloth` pipeline in SFT
I am trying to fine-tune the Mistral 7B quantized model and have introduced `task_type` as `token_cls`. However, I…
-
Thanks for the great work here!
I'm following along on the guide here to fine-tune the mixtral MoE version of Sphinx. https://github.com/Alpha-VLLM/LLaMA2-Accessory/tree/main/SPHINX#finetune-sphin…
-
### Motivation
Mistral 里面的 slidding window 对长上下文比较友好，qwen1.5里也有slidding window配置。请问turbomind有支持的计划么？
### Related resources
_No response_
### Additional context
_No response_