Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
OccamRazor
/
pythia-160m-deduped-gptq-4bit
like
1
Text Generation
Transformers
Safetensors
gpt_neox
Inference Endpoints
text-generation-inference
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
33ed16d
pythia-160m-deduped-gptq-4bit
1 contributor
History:
3 commits
OccamRazor
Use g instead of b for groupsize
33ed16d
about 1 year ago
.gitattributes
1.48 kB
initial commit
about 1 year ago
4bit-128g.safetensors
251 MB
LFS
Use g instead of b for groupsize
about 1 year ago
4bit.pt
248 MB
LFS
Add 4-bit quantizations of pythia-160m-deduped
about 1 year ago
config.json
569 Bytes
Add 4-bit quantizations of pythia-160m-deduped
about 1 year ago
special_tokens_map.json
99 Bytes
Add 4-bit quantizations of pythia-160m-deduped
about 1 year ago
tokenizer.json
2.11 MB
Add 4-bit quantizations of pythia-160m-deduped
about 1 year ago
tokenizer_config.json
404 Bytes
Add 4-bit quantizations of pythia-160m-deduped
about 1 year ago