Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
developer-lunark
/
kaidol-qwen3-14b-korean-rp
like
0
Text Generation
Transformers
KREW/korean-role-playing
Korean
English
qwen3
korean
role-playing
chat
conversational
fine-tuned
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
kaidol-qwen3-14b-korean-rp
/
global_step400
177 GB
1 contributor
History:
1 commit
developer-lunark
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
b2b059c
verified
6 days ago
bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch.FloatStorage"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch.FloatStorage"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch.FloatStorage"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch.FloatStorage"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch.FloatStorage"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch.FloatStorage"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"collections.OrderedDict"
,
"torch._tensor._rebuild_from_type_v2"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch.FloatStorage"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch._tensor._rebuild_from_type_v2"
How to fix it?
22.2 GB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_0_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_1_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_2_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_3_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_4_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_5_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_6_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
zero_pp_rank_7_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch.BFloat16Storage"
,
"collections.OrderedDict"
,
"__builtin__.set"
,
"torch.Size"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
224 kB
xet
Upload Qwen3-14B fine-tuned on Korean Role-Playing dataset
6 days ago
