|
--- |
|
language: |
|
- en |
|
- fr |
|
- de |
|
- es |
|
- it |
|
- pt |
|
- zh |
|
- ja |
|
- ru |
|
- ko |
|
license: other |
|
license_name: mrl |
|
base_model: mistralai/Pixtral-Large-Instruct-2411 |
|
inference: false |
|
license_link: https://mistral.ai/licenses/MRL-0.1.md |
|
library_name: transformers |
|
pipeline_tag: image-text-to-text |
|
--- |
|
|
|
# Pixtral-Large-Instruct-2411 🧡 |
|
|
|
Transformers implementation of [Pixtral-Large-Instruct-2411](https://huggingface.co/mistralai/Pixtral-Large-Instruct-2411). |
|
|
|
|
|
## Tokenizer And Prompt Template |
|
Using conversion of v7m1 tokenizer with 32k vocab size. |
|
|
|
Chat template in tokenizer_config.json uses the v7 instruct template: |
|
|
|
``` |
|
<s>[SYSTEM_PROMPT] <system prompt>[/SYSTEM_PROMPT][INST] <user message>[/INST] <assistant response></s>[INST] <user message>[/INST] |
|
``` |
|
|
|
## Notes |
|
*- tool use hasn't been implemented in the template yet. I'll add this in later.* |
|
*- I've added extra stop tokens between consecutive user messages. Helps contexts where there'll be multiple speakers etc but your milage may vary.* |
|
*- If you have a better implementation of the tokenizer let me know and I'm happy to swap it out.* |
|
*- As always pls respect the model license.* |
|
|
|
Currently doing a fresh measurement run ahead of re-doing my exl2 quants which I'll upload. Apologies in advance if anything is wonky, tbh this is just a personal learning exercise for me and I decided to make this model my fixation to freshen up on my knowledge lol. |
|
|
