bot-lab-21/GLM-5.3-Int4-Int8Mix-Pollard-GPTQ-MTP-Draft at main

GLM-5.3-Int4-Int8Mix-Pollard-GPTQ-MTP-Draft

13.1 GB

Ctrl+K

1 contributor

History: 2 commits

bot-lab-21

GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day)

10319bc verified 10 days ago

.gitattributes

1.57 kB
GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
README.md

3.44 kB
GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
chat_template.jinja

10.5 kB
GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
config.json

9.22 kB
GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
draft-00001.safetensors

4.29 GB
xet

GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
draft-00002.safetensors

4.29 GB
xet

GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
draft-00003.safetensors

2.41 GB
xet

GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
draft-00004.safetensors

2.07 GB
xet

GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
generation_config.json

194 Bytes
GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
model.safetensors.index.json

202 kB
GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
tokenizer.json

20.2 MB
xet

GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago
tokenizer_config.json

761 Bytes
GLM-5.3 MTP draft: layer 78 GPTQ int8-attention/int4-experts, standalone (1.84 vs 1.50 accepted/step same-day) 10 days ago