Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
marksverdhei
/
GLM-4.7-Flash-3L-pruned
like
0
Safetensors
glm4_moe_lite
Model card
Files
Files and versions
xet
Community
main
GLM-4.7-Flash-3L-pruned
4 GB
1 contributor
History:
2 commits
marksverdhei
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
d14026d
verified
20 days ago
.gitattributes
1.57 kB
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
20 days ago
chat_template.jinja
3.12 kB
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
20 days ago
config.json
1.07 kB
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
20 days ago
generation_config.json
181 Bytes
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
20 days ago
model.safetensors
3.98 GB
xet
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
20 days ago
tokenizer.json
20.2 MB
xet
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
20 days ago
tokenizer_config.json
7.23 kB
Initial upload: 3-layer pruned GLM-4.7-Flash (layer 0 dense + layers 1,46 MoE)
20 days ago
