Downloads · 30 days
4
20% of all-time downloads
Locutusque_-_TinyMistral-248M-v2-Instruct-4bits
RichardErkhov/Locutusque_-_TinyMistral-248M-v2-Instruct-4bits
Locutusque_-_TinyMistral-248M-v2-Instruct-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
20
Public
Parameters
251M
234 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors234 MB · 99%
Parameter types
How the weights are stored.
U8182M · 73%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
TinyMistral-248M-v2-Instruct - bnb 4bits
- Model creator: https://huggingface.co/Locutusque/
- Original model: https://huggingface.co/Locutusque/TinyMistral-248M-v2-Instruct/
Original model description:
license: apache-2.0 datasets:
- HuggingFaceH4/ultrachat_200k language:
- en
inference:
parameters:
do_sample: true
temperature: 0.1
top_p: 0.14
top_k: 12
max_new_tokens: 250
repetition_penalty: 1.1
widget:
- text: "<|im_start|>user\nHow do I incorporate visual elements into my writing?<|im_end|>\n<|im_start|>assistant\n" base_model: Locutusque/TinyMistral-248M-v2
Description
Fine-tuned Locutusque/TinyMistral-248M-v2 on the HuggingFaceH4/ultrachat_200k dataset.
Recommended inference parameters
do_sample: true
temperature: 0.1
top_p: 0.14
top_k: 12
repetition_penalty: 1.1
Recommended prompt template
<|im_start|>user\n{user message}<|im_end|>\n<|im_start|>assistant\n{assistant message}<|endoftext|>
Evaluation
This model will be submitted to the Open LLM Leaderboard.
- Type
- mistral
- Created
- Aug 27, 2024
- Updated
- Aug 27, 2024