Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
axel-datos
/
qwen2.5-0.5b-instruct_MATH_full-finetuningV2
like
0
Text Generation
Transformers
TensorBoard
Safetensors
customized
qwen2
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
qwen2.5-0.5b-instruct_MATH_full-finetuningV2
/
checkpoint-75
/
global_step75
1 contributor
History:
1 commit
axel-datos
Upload folder using huggingface_hub
c9be47f
verified
about 1 month ago
zero_pp_rank_0_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"torch._utils._rebuild_tensor_v2"
,
"torch.Size"
,
"torch.HalfStorage"
,
"__builtin__.set"
,
"collections.OrderedDict"
How to fix it?
144 kB
LFS
Upload folder using huggingface_hub
about 1 month ago
zero_pp_rank_0_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (8)
"torch.float16"
,
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"torch.Tensor"
,
"torch.FloatStorage"
,
"torch._tensor._rebuild_from_type_v2"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
,
"deepspeed.runtime.fp16.loss_scaler.DynamicLossScaler"
How to fix it?
5.93 GB
LFS
Upload folder using huggingface_hub
about 1 month ago