Skip to content

README.md

Latest commit

 

History

History
40 lines (29 loc) · 1.24 KB

README.md

File metadata and controls

40 lines (29 loc) · 1.24 KB

DeepSeek V4 Flash Test Vectors

These vectors were captured from the official DeepSeek V4 Flash API using deepseek-v4-flash, greedy decoding, thinking disabled, and top_logprobs=20. The hosted API does not expose full logits, so these files store the best logprob slice the API provides.

Files:

  • prompts/*.txt: exact user prompts.
  • official/*.official.json: official API continuations and top-logprobs.
  • official.vec: compact C-test fixture generated from the official JSON.

Regenerate official vectors:

DEEPSEEK_API_KEY=... ./tests/test-vectors/fetch_official_vectors.py

Running the fetcher without --only also regenerates official.vec.

The C runner consumes official.vec directly:

./ds4_test --logprob-vectors

official.vec is intentionally trivial to parse from C: each case points to a prompt file and each expected token is hex-encoded by bytes. The official JSON files remain in the tree so the compact fixture can be audited against the raw API response.

To inspect a local top-logprob dump manually:

./ds4 --metal --nothink -sys "" --temp 0 -n 4 --ctx 16384 \
  --prompt-file tests/test-vectors/prompts/long_code_audit.txt \
  --dump-logprobs /tmp/long_code_audit.ds4.json \
  --logprobs-top-k 20