Downloads · 30 days
109
17% of all-time downloads
Midnight-Miqu-70B-v1.5-W4A16-AutoRound
hoborific/Midnight-Miqu-70B-v1.5-W4A16-AutoRound
Midnight-Miqu-70B-v1.5-W4A16-AutoRound is a machine learning model from hoborific. 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
635
Public
Parameters
10.1B
36.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors36.7 GB · 100%
Parameter types
How the weights are stored.
I328.7B · 89%
Base models
Model card
From the Hugging Face model README
4-bit quant using Intel AutoRound
This is the default W4A16 scheme.
Quantization Details
at time of quantization, the default implied values not listed in the below json are as follows:
{"batch_size": 8, "iters": 200, "seqlen": 2048, "nsamples": 128, "lr": None}
quantization_config.json
{
"bits": 4,
"group_size": 128,
"sym": true,
"data_type": "int",
"low_gpu_mem_usage": true,
"autoround_version": "0.9.3",
"quant_method": "auto-round",
"packing_format": "auto_round:auto_gptq"
}
- Type
- llama
- Created
- Dec 11, 2025
- Updated
- Dec 11, 2025