Capability matrix
- Compute and format See GPT-2 conversion · Commodity x86 nightly lanes.
- Local entry point Raw continuation.
- Server Unverified for this artifact. Check for a service that accepts this artifact.
- Harness No recorded client task. Run one identified request, then a task with a checked result.
Choose the download
Publisher model card · CKE input files
Publisher task: text generation. CKE example: checkpoint from the published GPT-2 runner example. Use this artifact identifier:
hf://openai-community/gpt2.
Get started
Raw continuation model; do not apply an instruction chat template
version/v8/scripts/cks-v8-run run \
hf://openai-community/gpt2 \
--no-chat-template --allow-raw-prompt --max-tokens 64 --temperature 0.0 \
--prompt 'The sky was'What has actually run?
Coherent GGUF end-to-end nightly lanes. 1,024 tokens where recorded.
CPU evidence. Commodity x86 nightly lanes; provider selected from detected ISA.
Performance. The cited model result does not give a comparable prefill/decode pair here. ARM throughput for this exact artifact is unverified here. Benchmark evidence · 32K to 128K results
Can I fine-tune it?
Full-checkpoint training, LoRA and other PEFT methods: no verified CKE recipe for this exact checkpoint in the reviewed evidence. For a trainable starter, use the FP32 and adapter recipes.