2 contributors

History: 3 commits

huh707

integrate the folder of vicuna prune 0.20

42d7eb3 3 months ago

2024-04-29-02-02-34
integrate the folder of vicuna prune 0.20 3 months ago
.gitattributes

1.52 kB

initial commit 3 months ago
config.json

566 Bytes

integrate the folder of vicuna prune 0.20 3 months ago
description.txt

684 Bytes

integrate the folder of vicuna prune 0.20 3 months ago
generation_config.json

132 Bytes

integrate the folder of vicuna prune 0.20 3 months ago
pytorch_model.bin
Detected Pickle imports (23)
- "collections.OrderedDict",
- "LLMPruner.models.hf_llama.modeling_llama.LlamaRotaryEmbedding",
- "LLMPruner.models.hf_llama.modeling_llama.LlamaModel",
- "torch.nn.modules.activation.SiLU",
- "tokenizers.AddedToken",
- "LLMPruner.models.hf_llama.modeling_llama.LlamaAttention",
- "LLMPruner.models.hf_llama.modeling_llama.LlamaRMSNorm",
- "transformers.models.llama.configuration_llama.LlamaConfig",
- "transformers.tokenization_utils.Trie",
- "LLMPruner.models.hf_llama.modeling_llama.LlamaMLP",
- "torch.float16",
- "torch.nn.modules.sparse.Embedding",
- "transformers.generation.configuration_utils.GenerationConfig",
- "LLMPruner.models.hf_llama.modeling_llama.LlamaForCausalLM",
- "_codecs.encode",
- "torch._utils._rebuild_parameter",
- "__builtin__.set",
- "torch.HalfStorage",
- "torch.nn.modules.container.ModuleList",
- "torch._utils._rebuild_tensor_v2",
- "transformers.models.llama.tokenization_llama.LlamaTokenizer",
- "torch.nn.modules.linear.Linear",
- "LLMPruner.models.hf_llama.modeling_llama.LlamaDecoderLayer"
How to fix it?
11.4 GB
LFS

integrate the folder of vicuna prune 0.20 3 months ago
special_tokens_map.json

435 Bytes

integrate the folder of vicuna prune 0.20 3 months ago

Detected Pickle imports (23)