Buckets:
83.3 GB
3,227 files
Updated about 1 month ago
Ctrl+K
| Name | Size | Uploaded | Xet hash |
|---|---|---|---|
| CMakeLists.txt | 989 Bytes xet | 8c7b0094 | |
| README.md | 485 Bytes xet | 91ceafc1 | |
| lookup-create.cpp | 1.2 kB xet | 3f38f990 | |
| lookup-merge.cpp | 1.44 kB xet | f30faa54 | |
| lookup-stats.cpp | 5.79 kB xet | bfdb7bc1 | |
| lookup.cpp | 8.19 kB xet | 7ca7910c |
llama.cpp/examples/lookup
Demonstration of Prompt Lookup Decoding
https://github.com/apoorvumang/prompt-lookup-decoding
The key parameters for lookup decoding are ngram_min, ngram_max and n_draft. The first two determine the size of the ngrams to search for in the prompt for a match. The latter specifies how many subsequent tokens to draft if a match is found.
More info:
https://github.com/ggml-org/llama.cpp/pull/4484 https://github.com/ggml-org/llama.cpp/issues/4226
- Total size
- 83.3 GB
- Files
- 3,227
- Last updated
- Jul 8
- Pre-warmed CDN
- US EU US EU