Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
wassname
/
llama-3-2-1b-sft
like
0
Text Generation
Transformers
Safetensors
HuggingFaceH4/ultrachat_200k
llama
alignment-handbook
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
llama3.2
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
07f81f5
llama-3-2-1b-sft
/
checkpoint-3742
/
global_step3742
1 contributor
History:
1 commit
wassname
Upload folder using huggingface_hub
07f81f5
verified
4 months ago
bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
pickle
Detected Pickle imports (7)
"deepspeed.runtime.zero.config.ZeroStageEnum"
,
"collections.OrderedDict"
,
"torch.FloatStorage"
,
"torch._tensor._rebuild_from_type_v2"
,
"deepspeed.runtime.fp16.loss_scaler.LossScaler"
,
"torch.Tensor"
,
"torch._utils._rebuild_tensor_v2"
How to fix it?
14.8 GB
LFS
Upload folder using huggingface_hub
4 months ago
zero_pp_rank_0_mp_rank_00_model_states.pt
pickle
Detected Pickle imports (5)
"__builtin__.set"
,
"torch.BFloat16Storage"
,
"torch._utils._rebuild_tensor_v2"
,
"collections.OrderedDict"
,
"torch.Size"
How to fix it?
76.3 kB
LFS
Upload folder using huggingface_hub
4 months ago