1 contributor

History: 15 commits

anon8231489123

added ggml quantization for cuda model

4ef20dd over 1 year ago

gpt4-x-alpaca-13b-ggml-q4_1-from-gptq-4bit-128g
added ggml quantization for cuda model over 1 year ago
.gitattributes

1.48 kB

initial commit over 1 year ago
README.md

965 Bytes

Update README.md over 1 year ago
config.json

535 Bytes

Upload 8 files over 1 year ago
generation_config.json

137 Bytes

Upload 8 files over 1 year ago
ggml_README.txt

1.05 kB

added ggml quantization for cuda model over 1 year ago
gpt-x-alpaca-13b-native-4bit-128g-cuda.pt
Detected Pickle imports (4)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch.IntStorage",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
8.11 GB
LFS

Added cuda GPTQ branch model. over 1 year ago
gpt-x-alpaca-13b-native-4bit-128g.pt
Detected Pickle imports (5)
- "torch._utils._rebuild_tensor_v2",
- "torch.IntStorage",
- "collections.OrderedDict",
- "torch.HalfStorage",
- "torch.FloatStorage"
What is a pickle import?
7.91 GB
LFS

Upload gpt-x-alpaca-13b-native-4bit-128g.pt over 1 year ago
pytorch_model.bin.index.json

33.4 kB

Upload 8 files over 1 year ago
special_tokens_map.json

96 Bytes

Upload 8 files over 1 year ago
tokenizer.model

500 kB
LFS

Upload 8 files over 1 year ago
tokenizer_config.json

329 Bytes

Upload 8 files over 1 year ago
trainer_state.json

101 kB

Upload 8 files over 1 year ago
training_args.bin
Detected Pickle imports (7)
- "transformers.trainer_utils.FSDPOption",
- "transformers.trainer_utils.IntervalStrategy",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "torch.device",
- "__main__.TrainingArguments",
- "transformers.training_args.OptimizerNames"
How to fix it?
3.71 kB
LFS

Upload 8 files over 1 year ago

Detected Pickle imports (4)

Detected Pickle imports (5)

Detected Pickle imports (7)