Darkstorm1826
/

base-gpt2xl-better-sft

anti-hallucination

Model card Files Files and versions

base-gpt2xl-better-sft

6.56 GB

Ctrl+K

Ctrl+K

1 contributor

History: 4 commits

Darkstorm1826's picture

Hard repair GPT-2 XL output degeneration and hallucination behavior with safetensors metadata fix

4a0fff4 verified 24 days ago

.gitattributes

1.52 kB
initial commit 25 days ago
README.md

871 Bytes
Hard repair GPT-2 XL output degeneration and hallucination behavior with safetensors metadata fix 24 days ago
added_tokens.json

113 Bytes
Upload continued GPT-2 XL SFT checkpoint 25 days ago
config.json

901 Bytes
Hard repair GPT-2 XL output degeneration and hallucination behavior with safetensors metadata fix 24 days ago
hard_repair_preview.jsonl

110 kB
Hard repair GPT-2 XL output degeneration and hallucination behavior with safetensors metadata fix 24 days ago
jax_hard_repair_config.json

894 Bytes
Hard repair GPT-2 XL output degeneration and hallucination behavior with safetensors metadata fix 24 days ago
jax_training_config.json

769 Bytes
Continue GPT-2 XL better SFT with anti-hallucination JAX TPU pass 25 days ago
merges.txt

456 kB
Upload continued GPT-2 XL SFT checkpoint 25 days ago
model.safetensors

6.55 GB
xet

Hard repair GPT-2 XL output degeneration and hallucination behavior with safetensors metadata fix 24 days ago
special_tokens_map.json

685 Bytes
Upload continued GPT-2 XL SFT checkpoint 25 days ago
tokenizer.json

3.56 MB
Upload continued GPT-2 XL SFT checkpoint 25 days ago
tokenizer_config.json

1.48 kB
Upload continued GPT-2 XL SFT checkpoint 25 days ago
vocab.json

798 kB
Upload continued GPT-2 XL SFT checkpoint 25 days ago