1 contributor

History: 3 commits

pavan01729

Upload gptq_4_llama_7b_hf_whitening_0.65.pt with huggingface_hub

a913626 verified 2 months ago

.gitattributes

1.52 kB

initial commit 2 months ago
gptq_4_llama_7b_hf_whitening_0.65.pt
Detected Pickle imports (24)
- "component.svd_llama.LlamaRotaryEmbedding",
- "torch.nn.modules.linear.Linear",
- "transformers.tokenization_utils.Trie",
- "_codecs.encode",
- "transformers.models.llama.modeling_llama.LlamaForCausalLM",
- "__builtin__.set",
- "transformers.models.llama.tokenization_llama.LlamaTokenizer",
- "transformers.models.llama.modeling_llama.LlamaModel",
- "torch._utils._rebuild_tensor_v2",
- "transformers.activations.SiLUActivation",
- "transformers.models.llama.modeling_llama.LlamaRMSNorm",
- "torch.float16",
- "collections.OrderedDict",
- "torch._utils._rebuild_parameter",
- "transformers.models.llama.configuration_llama.LlamaConfig",
- "component.svd_llama.SVD_LlamaMLP",
- "torch.device",
- "component.svd_llama.SVD_LlamaAttention",
- "transformers.generation.configuration_utils.GenerationConfig",
- "torch.HalfStorage",
- "tokenizers.AddedToken",
- "torch.nn.modules.container.ModuleList",
- "transformers.models.llama.modeling_llama.LlamaDecoderLayer",
- "torch.nn.modules.sparse.Embedding"
How to fix it?
8.98 GB
LFS

Upload gptq_4_llama_7b_hf_whitening_0.65.pt with huggingface_hub 2 months ago
gptq_4_llama_7b_hf_whitening_0.8.pt
Detected Pickle imports (24)
- "torch._utils._rebuild_parameter",
- "torch.nn.modules.sparse.Embedding",
- "torch.nn.modules.linear.Linear",
- "transformers.models.llama.configuration_llama.LlamaConfig",
- "torch.float16",
- "_codecs.encode",
- "torch.nn.modules.container.ModuleList",
- "transformers.activations.SiLUActivation",
- "transformers.models.llama.modeling_llama.LlamaRMSNorm",
- "transformers.models.llama.modeling_llama.LlamaForCausalLM",
- "collections.OrderedDict",
- "__builtin__.set",
- "transformers.models.llama.modeling_llama.LlamaModel",
- "transformers.models.llama.tokenization_llama.LlamaTokenizer",
- "component.svd_llama.SVD_LlamaAttention",
- "tokenizers.AddedToken",
- "torch.device",
- "component.svd_llama.SVD_LlamaMLP",
- "torch.HalfStorage",
- "transformers.generation.configuration_utils.GenerationConfig",
- "transformers.models.llama.modeling_llama.LlamaDecoderLayer",
- "component.svd_llama.LlamaRotaryEmbedding",
- "torch._utils._rebuild_tensor_v2",
- "transformers.tokenization_utils.Trie"
How to fix it?
10.9 GB
LFS

Upload gptq_4_llama_7b_hf_whitening_0.8.pt with huggingface_hub 2 months ago

Detected Pickle imports (24)

Detected Pickle imports (24)