Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
base-gpt2xl-better-sft-experimental – AI Model by Darkstorm1826 | AlphaNeural AI
You can deploy this model and start earning money today!
Darkstorm1826
/
base-gpt2xl-better-sft-experimental
like
0
safetensors
gpt2
gpt2-xl
assistant
jax
optax
tpu
instruction-tuning
chat
coherence
huggingface-datasets
Darkstorm1826/base-gpt2xl-better-sft-experimental
finetune
mit
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
Base GPT-2 XL Better SFT — HF-Only Assistant Coherence Continuation
Continuation checkpoint trained from
Darkstorm1826/base-gpt2xl-better-sft-experimental
using a JAX/Optax TPU full fine-tune pass.
This experimental continuation uses
/kaggle/working/distilled.jsonl
, built only from Hugging Face datasets.
Focus:
broader assistant behavior
chat/instruction following
creative writing
everyday procedural answers
context-grounded QA
truthfulness and hallucination reduction
cleaner stopping behavior
Prompt format:
<|system|> You are a helpful, honest, and careful AI assistant.<|end|> <|user|> Question here<|end|> <|assistant|> Answer here<|end|>
