Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
CanadaApollo6
/
M3TiS-33B
Like
0
Text Generation
Safetensors
English
Chinese
llama
nanbeige
exl3
speculative-decoding
dflash
cuda
rtx-3090
tool-calling
tensorfold
m3tis
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
M3TiS-33B
20.9 GB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
CanadaApollo6
config.json: drop the float quantization_config.bits (the Hub requires an int); 3.5 stays in quantization_config.json
6f4bc66
verified
11 days ago
LICENSES
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
bin
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
draft
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
.gitattributes
1.63 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
LICENSE
11.4 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
NOTICE
1.13 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
README.md
9.02 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
SOURCE.md
1.2 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
THIRD_PARTY_NOTICES.md
27.9 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
added_tokens.json
174 Bytes
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
config.json
1.22 kB
config.json: drop the float quantization_config.bits (the Hub requires an int); 3.5 stays in quantization_config.json
11 days ago
generation_config.json
164 Bytes
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
m3tis-serve.sh
726 Bytes
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
model-00001-of-00002.safetensors
8.35 GB
xet
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
model-00002-of-00002.safetensors
8.4 GB
xet
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
model.safetensors.index.json
131 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
quantization_config.json
471 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
special_tokens_map.json
623 Bytes
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
tokenizer.json
18.5 MB
xet
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
tokenizer.model
2.78 MB
xet
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
tokenizer_config.json
11 kB
M3TiS-33B: Nanbeige4.3-33B EXL3 3.5 bpw + DFlash2 draft head + TensorFold server (engine aacb6300)
11 days ago
