danny0122
/

Llama-2-7b-hf-GPTQ-4bits-gr128-nsf

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Llama-2-7b-hf-GPTQ-4bits-gr128-nsf

1 contributor

History: 2 commits

danny0122's picture

AutoGPTQ model for meta-llama/Llama-2-7b-hf: 4bits, gr128, desc_act=False

8fadec9 12 months ago

.gitattributes

1.52 kB

initial commit 12 months ago
config.json

689 Bytes

AutoGPTQ model for meta-llama/Llama-2-7b-hf: 4bits, gr128, desc_act=False 12 months ago
gptq_model-4bit-128g.bin
Detected Pickle imports (4)
- "torch.HalfStorage",
- "torch._utils._rebuild_tensor_v2",
- "torch.IntStorage",
- "collections.OrderedDict"
What is a pickle import?
3.9 GB
LFS

AutoGPTQ model for meta-llama/Llama-2-7b-hf: 4bits, gr128, desc_act=False 12 months ago
quantize_config.json

211 Bytes

AutoGPTQ model for meta-llama/Llama-2-7b-hf: 4bits, gr128, desc_act=False 12 months ago