vocab : support tokenizer for LFM2.5-8B-A1B (#23826)
* vocab: Support tokenizer for LFM2.5-8B-A1B * Keep liquid6 tokenizer in models
This commit is contained in:
@@ -139,7 +139,7 @@ models = [
|
||||
{"name": "seed-coder", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Base", },
|
||||
{"name": "a.x-4.0", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/skt/A.X-4.0", },
|
||||
{"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": "lfm2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LiquidAI/LFM2.5-350M", },
|
||||
{"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", },
|
||||
{"name": "modern-bert", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/answerdotai/ModernBERT-base", },
|
||||
@@ -183,6 +183,8 @@ pre_computed_hashes = [
|
||||
# jina-v2-de variants
|
||||
{"name": "jina-v2-de", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/aari1995/German_Semantic_V3", "chkhsh": "b3d1dd861f1d4c5c0d2569ce36baf3f90fe8a102db3de50dd71ff860d91be3df"},
|
||||
{"name": "gpt-2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/evilfreelancer/ruGPT3XL", "chkhsh": "0fe1cf6eda062318a1af7270f3331a85c539a01778ff948e24388e949c5282f4"},
|
||||
# lfm2 variants
|
||||
{"name": "lfm2", "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/LiquidAI/LFM2.5-8B-A1B", "chkhsh": "9e454714343b69b99b71795c1d27a68c2a1d15dab111f4d353109f966af29da7"},
|
||||
]
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user