Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
seonglae
/
llama-2-13b-chat-hf-gptq
like
0
Text Generation
Transformers
llama
llama-2
llama2
gptq
auto-gptq
13b
4bit
quantization
text-generation-inference
License:
other
Model card
Files
Files and versions
Community
1
Train
Deploy
Use this model
790948d
llama-2-13b-chat-hf-gptq
1 contributor
History:
12 commits
seonglae
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
790948d
about 1 year ago
.gitattributes
1.52 kB
initial commit
about 1 year ago
README.md
995 Bytes
Update README.md
about 1 year ago
added_tokens.json
21 Bytes
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
config.json
631 Bytes
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
generation_config.json
170 Bytes
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
gptq_model-4bit-128g.bin
pickle
Detected Pickle imports (5)
"torch.HalfStorage"
,
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch.IntStorage"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
7.26 GB
LFS
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
gptq_model-4bit-128g.safetensors
7.26 GB
LFS
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
quantize_config.json
185 Bytes
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
special_tokens_map.json
414 Bytes
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
tokenizer.json
1.84 MB
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
tokenizer.model
500 kB
LFS
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago
tokenizer_config.json
698 Bytes
build: AutoGPTQ for meta-llama/Llama-2-13b-chat-hf: 4bits, gr128, desc_act=False
about 1 year ago