Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

unsloth
/
GLM-4.7-Flash-FP8-Dynamic

Text Generation
Transformers
Safetensors
English
Chinese
glm4_moe_lite
unsloth
conversational
compressed-tensors
Model card Files Files and versions
xet
Community
4
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Trying to serve with vllm, got this error: ValueError: There is no module or parameter named 'model.layers.1.mlp.gate.e_score_correction_bias' in TransformersMoEForCausalLM

➕ 1
5
#4 opened 3 days ago by
firow2

vllm nightly currently not supporting Blackwell with this model

1
#3 opened 5 days ago by
1anH

Severe Looping/Repetitive Output when using --kv-cache-dtype fp8 with GLM-4.7-Flash-FP8-Dynamic on vLLM

4
#2 opened 5 days ago by
ShelterW

dual 3090 inference

5
#1 opened 6 days ago by
evetsagg
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs