tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-14 12:19:48 -04:00
Code Issues Packages Projects Releases Wiki Activity

vocab : JetBrains Mellum pre-tokenizer (#15045)

Browse Source
This commit is contained in:
Csaba Kecskemeti
2025-08-03 12:38:18 -07:00
committed by GitHub
parent 83bc2f288c
commit 97366dc6ab
3 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
convert_hf_to_gguf_update.py
View File

@@ -138,6 +138,7 @@ models = [
{"name": "midm-2.0", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/K-intelligence/Midm-2.0-Base-Instruct", },
{"name": "lfm2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LiquidAI/LFM2-Tokenizer"},
{"name": "exaone4", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LGAI-EXAONE/EXAONE-4.0-32B", },
{"name": "mellum", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/JetBrains/Mellum-4b-base", },
]
# some models are known to be broken upstream, so we will skip them as exceptions