boadisamson
/

CodeLlama-8b-gptq-4bit-Instruct-hf

Text Generation

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

CodeLlama-8b-gptq-4bit-Instruct-hf

1 contributor

History: 2 commits

boadisamson's picture

Upload of AutoGPTQ quantized model

15120a9 verified 10 months ago

.gitattributes

1.52 kB

initial commit 10 months ago
config.json

1.01 kB

Upload of AutoGPTQ quantized model 10 months ago
gptq_model-4bit-128g.bin
Detected Pickle imports (4)
- "torch._utils._rebuild_tensor_v2",
- "torch.IntStorage",
- "collections.OrderedDict",
- "torch.HalfStorage"
What is a pickle import?
4.49 GB
LFS

Upload of AutoGPTQ quantized model 10 months ago
gptq_model-4bit-128g.safetensors

3.9 GB
LFS

Upload of AutoGPTQ quantized model 10 months ago
quantize_config.json

265 Bytes

Upload of AutoGPTQ quantized model 10 months ago