Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ondevicellm
/
tinyllama_moe_sft_ultrachat200k_v2_epochs5
like
0
Follow
On-Device-LLM
4
Text Generation
Transformers
TensorBoard
Safetensors
HuggingFaceH4/ultrachat_200k
mixtral
alignment-handbook
Generated from Trainer
trl
sft
conversational
text-generation-inference
License:
apache-2.0
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
051fe8e
tinyllama_moe_sft_ultrachat200k_v2_epochs5
Ctrl+K
Ctrl+K
1 contributor
History:
52 commits
hushell
Training in progress, step 5700
051fe8e
verified
over 1 year ago
runs
Training in progress, step 5700
over 1 year ago
.gitattributes
Safe
1.52 kB
initial commit
over 1 year ago
config.json
Safe
835 Bytes
Training in progress, step 100
over 1 year ago
special_tokens_map.json
Safe
550 Bytes
Training in progress, step 100
over 1 year ago
tokenizer.json
Safe
1.84 MB
Training in progress, step 100
over 1 year ago
tokenizer_config.json
Safe
1.42 kB
Training in progress, step 100
over 1 year ago
training_args.bin
pickle
Detected Pickle imports (11)
"transformers.trainer_utils.HubStrategy"
,
"torch.device"
,
"alignment.configs.SFTConfig"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.integrations.deepspeed.HfTrainerDeepSpeedConfig"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DeepSpeedPlugin"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.state.PartialState"
,
"torch.bfloat16"
How to fix it?
5.82 kB
LFS
Training in progress, step 100
over 1 year ago