PrunaAI

/

microsoft-Phi-3-small-8k-instruct-QUANTO-float8bit-smashed

like 0

• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.configuration_phi3_small.Phi3SmallConfig",
• "quanto.nn.qlinear.QLinear",
• "torch.nn.modules.container.ModuleList",
• "torch.device",
• "__builtin__.set",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.triton_blocksparse_attention_layer.BlockSparseAttentionLayer",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.modeling_phi3_small.Phi3SmallModel",
• "torch.BoolStorage",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.modeling_phi3_small.Phi3SmallMLP",
• "collections.OrderedDict",
• "torch._utils._rebuild_parameter",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.modeling_phi3_small.Phi3SmallSelfAttention",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.modeling_phi3_small.Phi3SmallDecoderLayer",
• "torch.nn.modules.dropout.Dropout",
• "torch.FloatStorage",
• "transformers.generation.configuration_utils.GenerationConfig",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.triton_flash_blocksparse_attn.BlockSparseParams",
• "quanto.tensor.qtype.qtype",
• "torch._utils._rebuild_tensor_v2",
• "torch.BFloat16Storage",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.modeling_phi3_small.Phi3SmallForCausalLM",
• "torch.nn.modules.normalization.LayerNorm",
• "torch.bfloat16",
• "transformers_modules.microsoft.Phi-3-small-8k-instruct.69caae1f2acea34b26f535fecb1f2abb9a304695.positional_embedding.RotaryEmbedding",
• "torch.nn.modules.sparse.Embedding",
• "torch.float8_e4m3fn"

How to fix it?