Skip to content

Actions: ngxson/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pre-tokenizer-hashes.yml
18 workflow run results
18 workflow run results

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

convert : make Mistral community chat templates optional via paramete… Check Pre-Tokenizer Hashes #18: Commit b2caf67 pushed by ngxson
32s master
master
32s
fix style Check Pre-Tokenizer Hashes #17: Commit 9bba547 pushed by ngxson
31s xsn/kimi-vl
xsn/kimi-vl
31s
clean up Check Pre-Tokenizer Hashes #16: Commit afd43a9 pushed by ngxson
30s xsn/kimi-vl
xsn/kimi-vl
30s
convert : force patch_embd weights to F16 or F32 to avoid broken GGUF… Check Pre-Tokenizer Hashes #15: Commit 4d19698 pushed by ngxson
29s master
master
29s
model : support vision LiquidAI LFM2-VL family (#15347) Check Pre-Tokenizer Hashes #14: Commit 65349f2 pushed by ngxson
31s master
master
31s
lfm2 vision model, for discussion Check Pre-Tokenizer Hashes #13: Pull request #28 opened by ngxson
32s xsn/lfm2_vl
xsn/lfm2_vl
32s
wip lfm2 vision model Check Pre-Tokenizer Hashes #12: Commit 955b18e pushed by ngxson
30s xsn/lfm2_vl
xsn/lfm2_vl
30s
convert : fix merge conflicts (#15229) Check Pre-Tokenizer Hashes #11: Commit 50e81bd pushed by ngxson
29s master
master
29s
convert : improve Mistral models integration (#14737) Check Pre-Tokenizer Hashes #10: Commit a3a7874 pushed by ngxson
55s master
master
55s
convert : support non-mxfp4 HF model (#15153) Check Pre-Tokenizer Hashes #9: Commit 50aa938 pushed by ngxson
31s master
master
31s
disable debug check Check Pre-Tokenizer Hashes #8: Commit bbe8c21 pushed by ngxson
28s xsn/gptoss_non_mxfp4_conversion
xsn/gptoss_non_mxfp4_conversion
28s
llama : Support intern-s1 (#14875) Check Pre-Tokenizer Hashes #7: Commit 99acbc9 pushed by ngxson
31s master
master
31s
convert : support non-mxfp4 HF model Check Pre-Tokenizer Hashes #6: Commit b1cbcdd pushed by ngxson
27s xsn/gptoss_non_mxfp4_conversion
xsn/gptoss_non_mxfp4_conversion
27s
llama : add gpt-oss (#15091) Check Pre-Tokenizer Hashes #5: Commit fd1234c pushed by ngxson
31s master
master
31s
model: support GLM 4.5 family of models (#14939) Check Pre-Tokenizer Hashes #4: Commit ef0144c pushed by ngxson
28s master
master
28s
vocab : JetBrains Mellum pre-tokenizer (#15045) Check Pre-Tokenizer Hashes #3: Commit 97366dc pushed by ngxson
35s master
master
35s
model : add text-only support for Kimi-VL (and find special tokens in… Check Pre-Tokenizer Hashes #2: Commit 83bc2f2 pushed by ngxson
30s master
master
30s
ci : check that pre-tokenizer hashes are up-to-date (#15032) Check Pre-Tokenizer Hashes #1: Commit 2bf3fbf pushed by ngxson
30s master
master
30s