Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
DoodDood
/
TOMAGPT
like
0
Text Generation
Safetensors
DoodDood/HearsayGRPOTrainingData2
qwen3
legal
hearsay
classification
grpo
reinforcement-learning
legalbench
lora
conversational
Eval Results (legacy)
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
TOMAGPT
8.06 GB
1 contributor
History:
2 commits
DoodDood
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
00f3029
verified
17 days ago
.gitattributes
1.57 kB
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
README.md
4.46 kB
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
chat_template.jinja
2.63 kB
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
config.json
1.59 kB
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
generation_config.json
212 Bytes
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
model.safetensors
8.04 GB
xet
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
tokenizer.json
11.4 MB
xet
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
tokenizer_config.json
666 Bytes
Upload TOMAGPT: Qwen3-4B + GRPO hearsay LoRA (Run 3, 500 steps)
17 days ago
