-
I'm not sure if it's a bug/feature, sometimes modifying the normalizer of a pretrained tokenizer works but sometimes it doesn't.
For example, it works for `"mistralai/Mistral-7B-v0.1"` but not `"m…
-
```
export MODEL=mistralai/Mistral-7B-v0.1
python3 -m vllm.entrypoints.openai.api_server --model $MODEL \
--tensor-parallel-size=1 \
--enable-prefix-caching --max-model-len=4096 --trust-re…
-
Checking the constraints to add Mistral 7B
in the list of models.
It seems it has been benchmarked with auto-awq :
https://github.com/casper-hansen/AutoAWQ
-
### Prerequisites
- [X] I am running the latest code. Mention the version if possible as well.
- [X] I carefully followed the [README.md](https://github.com/ggerganov/llama.cpp/blob/master/README.md)…
-
In the **"5. Preference Alignment"** section, the link in **"Fine-tune Mistral-7b with DPO"** refers to a Huggingface article about how to fine-tune llama2 with RLHF NOT Mistral-7b, I guess the correc…
-
Any reasons why mistralai_mistral-7b-instruct-v0.2 does not offload on gpu ?
load INSTRUCTOR_Transformer
max_seq_length 512
Starting get_model: llama
Failed to listen to n_gpus: No modu…
-
Nice work.
I am trying to use fastchat to train a mistral model. however, I wonder why the following code is hard code for only vicuna.
[https://github.com/lm-sys/FastChat/blob/main/fastchat/train/…
-
Error for 4.39.3
```
Traceback (most recent call last):
File "/home/arda/kai/webui/text-generation-webui/modules/callbacks.py", line 61, in gentask
ret = self.mfunc(callback=_callback, *args…
-
### System Info
Nvidia GPU A100*8
Linux OS
```
❯ /usr/local/cuda/bin/nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2023 NVIDIA Corpor…
-
### 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.
…