Skip to content

Actions: ggml-org/llama.cpp

Actions

Check Pre-Tokenizer Hashes

Actions

Loading...
Loading

Show workflow options

Create status badge

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

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

model : add LightOnOCR-1B model Check Pre-Tokenizer Hashes #604: Pull request #16764 opened by ngxson
55s ngxson:xsn/lighton-ocr
ngxson:xsn/lighton-ocr
55s
convert: Handle mmproj model output filename properly Check Pre-Tokenizer Hashes #603: Pull request #16760 synchronize by Galunid
1m 1s Galunid:fix-mmproj-filename
Galunid:fix-mmproj-filename
1m 1s
convert: Handle mmproj model output filename properly Check Pre-Tokenizer Hashes #602: Pull request #16760 opened by Galunid
57s Galunid:fix-mmproj-filename
Galunid:fix-mmproj-filename
57s
convert : avoid dequantizing mxfp4 for GPT-OSS Check Pre-Tokenizer Hashes #601: Pull request #16756 opened by compilade
59s compilade/fix-prequant-mxfp4-gpt-oss
compilade/fix-prequant-mxfp4-gpt-oss
59s
convert : avoid dequantizing mxfp4 for GPT-OSS Check Pre-Tokenizer Hashes #600: Commit d7f794e pushed by compilade
1m 0s compilade/fix-prequant-mxfp4-gpt-oss
compilade/fix-prequant-mxfp4-gpt-oss
1m 0s
convert : fix GPT-OSS mxfp4 wrongly failing Check Pre-Tokenizer Hashes #599: Commit 3c1c192 pushed by compilade
1m 1s compilade/fix-prequant-mxfp4-gpt-oss
compilade/fix-prequant-mxfp4-gpt-oss
1m 1s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #598: Pull request #16749 synchronize by pockers21
18m 1s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
18m 1s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #597: Pull request #16749 synchronize by pockers21
57s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
57s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #596: Pull request #16749 synchronize by pockers21
58s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
58s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #595: Pull request #16749 synchronize by pockers21
59s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
59s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #594: Pull request #16749 synchronize by pockers21
54s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
54s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #593: Pull request #16749 synchronize by pockers21
56s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
56s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #592: Pull request #16749 synchronize by pockers21
56s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
56s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #591: Pull request #16749 synchronize by pockers21
55s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
55s
convert: clean Gemma vision/audio chat template markers Check Pre-Tokenizer Hashes #590: Pull request #16749 opened by pockers21
1m 1s pockers21:bugfix-server-vision-mtmd
pockers21:bugfix-server-vision-mtmd
1m 1s
mtmd: Add JinaCLIP v2 vision projector + GGUF support for jina-bert-v3 (merged-LoRA or adapter) Check Pre-Tokenizer Hashes #589: Pull request #16574 synchronize by pockers21
59s pockers21:feature/jinaclip-v2-projector
pockers21:feature/jinaclip-v2-projector
59s
convert : handle pre-quantized models (#14810) Check Pre-Tokenizer Hashes #588: Commit f8f071f pushed by compilade
2m 4s master
master
2m 4s
Model: Qwen3 Next Check Pre-Tokenizer Hashes #587: Pull request #16095 synchronize by pwilkin
37m 22s pwilkin:qwen3_next
pwilkin:qwen3_next
37m 22s
Model: Qwen3 Next Check Pre-Tokenizer Hashes #586: Pull request #16095 synchronize by pwilkin
21m 35s pwilkin:qwen3_next
pwilkin:qwen3_next
21m 35s
Model: Qwen3 Next Check Pre-Tokenizer Hashes #585: Pull request #16095 synchronize by pwilkin
32m 7s pwilkin:qwen3_next
pwilkin:qwen3_next
32m 7s
Model: Qwen3 Next Check Pre-Tokenizer Hashes #584: Pull request #16095 synchronize by pwilkin
29m 38s pwilkin:qwen3_next
pwilkin:qwen3_next
29m 38s
Merge branch 'master' into compilade/convert-prequant Check Pre-Tokenizer Hashes #583: Commit 93fbd40 pushed by compilade
30m 48s compilade/convert-prequant
compilade/convert-prequant
30m 48s
convert : handle pre-quantized models Check Pre-Tokenizer Hashes #582: Pull request #14810 synchronize by compilade
34m 48s compilade/convert-prequant
compilade/convert-prequant
34m 48s
Model: Qwen3 Next Check Pre-Tokenizer Hashes #581: Pull request #16095 synchronize by pwilkin
1h 7m 58s pwilkin:qwen3_next
pwilkin:qwen3_next
1h 7m 58s
Model: Qwen3 Next Check Pre-Tokenizer Hashes #580: Pull request #16095 synchronize by pwilkin
1h 5m 10s pwilkin:qwen3_next
pwilkin:qwen3_next
1h 5m 10s