Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
UVLabs
/
HyperLLM-4b
like
3
Follow
UV Labs
6
Text Generation
PEFT
Safetensors
custom
English
trading
hyperliquid
finance
lora
dora
dpo
conversational
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
HyperLLM-4b
549 MB
1 contributor
History:
7 commits
bebis1
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
aef556a
verified
about 14 hours ago
.gitattributes
Safe
1.57 kB
Initial release v0.1 - experimental
10 days ago
LICENSE
Safe
11 kB
Initial release v0.1 - experimental
10 days ago
README.md
6.95 kB
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
about 14 hours ago
adapter_config.json
1.06 kB
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
about 14 hours ago
adapter_model.safetensors
533 MB
xet
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
about 14 hours ago
added_tokens.json
Safe
707 Bytes
Upload HyperLLM v0.2
8 days ago
chat_template.jinja
Safe
2.63 kB
Upload HyperLLM v0.2
8 days ago
merges.txt
Safe
1.67 MB
Upload HyperLLM v0.2
8 days ago
special_tokens_map.json
Safe
613 Bytes
Upload HyperLLM v0.2
8 days ago
tokenizer.json
Safe
11.4 MB
xet
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
about 14 hours ago
tokenizer_config.json
Safe
5.41 kB
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
about 14 hours ago
training_args.bin
pickle
Detected Pickle imports (11)
"transformers.trainer_utils.SaveStrategy"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SchedulerType"
,
"accelerate.state.PartialState"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.HubStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"torch.device"
,
"trl.trainer.dpo_config.DPOConfig"
,
"transformers.training_args.OptimizerNames"
,
"trl.trainer.dpo_config.FDivergenceType"
How to fix it?
6.8 kB
xet
Upload HyperLLM v0.4 - DoRA + DPO training with +11.1% accuracy improvement
about 14 hours ago
vocab.json
Safe
2.78 MB
Upload HyperLLM v0.2
8 days ago