Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
bobber
/
routangseng-0.8b-hottake
like
0
Safetensors
Chinese
qwen3_5_text
chinese
political-analysis
distillation
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
routangseng-0.8b-hottake
1.52 GB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
bobber
Add model card with GitHub CDN and ONNX links
87e5cf2
verified
4 months ago
.gitattributes
Safe
1.57 kB
Phase 11: 0.8B hot-take distilled from Phase 10 Think-SFT (949 condensed examples, heuristic eval 4.60/5)
4 months ago
README.md
1.35 kB
Add model card with GitHub CDN and ONNX links
4 months ago
chat_template.jinja
Safe
7.76 kB
Phase 11: 0.8B hot-take distilled from Phase 10 Think-SFT (949 condensed examples, heuristic eval 4.60/5)
4 months ago
config.json
Safe
1.8 kB
Phase 11: 0.8B hot-take distilled from Phase 10 Think-SFT (949 condensed examples, heuristic eval 4.60/5)
4 months ago
generation_config.json
Safe
168 Bytes
Phase 11: 0.8B hot-take distilled from Phase 10 Think-SFT (949 condensed examples, heuristic eval 4.60/5)
4 months ago
model.safetensors
Safe
1.5 GB
xet
Phase 11 v3: longer responses (200-400 chars), retrained 0.8B
4 months ago
tokenizer.json
Safe
20 MB
xet
Phase 11: 0.8B hot-take distilled from Phase 10 Think-SFT (949 condensed examples, heuristic eval 4.60/5)
4 months ago
tokenizer_config.json
Safe
1.1 kB
Phase 11: 0.8B hot-take distilled from Phase 10 Think-SFT (949 condensed examples, heuristic eval 4.60/5)
4 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
,
"transformers.trainer_utils.SchedulerType"
,
"torch.device"
,
"trl.trainer.sft_config.SFTConfig"
,
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.IntervalStrategy"
,
"transformers.trainer_utils.SaveStrategy"
,
"accelerate.state.PartialState"
How to fix it?
5.65 kB
xet
Phase 11 v3: longer responses (200-400 chars), retrained 0.8B
4 months ago