Downloads · 30 days
0
0% of all-time downloads
Quant-Cartel/mini-magnum-12b-v1.1-exl2-longcal
mini-magnum-12b-v1.1-exl2-longcal is a machine learning model from Quant-Cartel. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Quantized using 115 rows of 8192 tokens from the default ExLlamav2-calibration dataset.
Downloads · 30 days
0
0% of all-time downloads
All-time downloads
3
Public
Repo size
35 GB
Likes
3
Public
Click a slice to open those files.
.json2.2 MB · 80%
From the Hugging Face model README
e88 88e d8
d888 888b 8888 8888 ,"Y88b 888 8e d88
C8888 8888D 8888 8888 "8" 888 888 88b d88888
Y888 888P Y888 888P ,ee 888 888 888 888
"88 88" "88 88" "88 888 888 888 888
b
8b,
e88'Y88 d8 888
d888 'Y ,"Y88b 888,8, d88 ,e e, 888
C8888 "8" 888 888 " d88888 d88 88b 888
Y888 ,d ,ee 888 888 888 888 , 888
"88,d88 "88 888 888 888 "YeeP" 888
PROUDLY PRESENTS
Quantized using 115 rows of 8192 tokens from the default ExLlamav2-calibration dataset.
Branches:
main -- measurement.json8b8h -- 8bpw, 8bit lm_head6b8h -- 6bpw, 8bit lm_head4b6h -- 4bpw, 6bit lm_head2.25b6h -- 2.25bpw, 6bit lm_headOriginal model link: intervitens/mini-magnum-12b-v1.1
As apparently the default dataset is supposed to be better in nearly all situations, I decided to start quanting using that in addition to my standard rpcal-fare. I'd appreciate real-world tests to confirm the hypothesis, though, so please leave a comment if you find this mode of quanting better than rpcal.
Original model README below.

This model is the miniature version of alpindale/magnum-72b-v1, a second entry in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Mistral-Nemo-Base-2407. A new general purpose instruction dataset by kalomaze was added to the training mix for better coherence and general alignment. We are working on improving our dataset and training procedures, so expect new versions to come out soon.
Model has been Instruct tuned with the Mistral formatting. A typical input would look like this:
"""[INST] Hi there! [/INST]Nice to meet you!</s>[INST] Can I ask a question? [/INST]
"""
This model has been a team effort, credits go to:
...