LangMAP

company

https://cimeister.github.io/blog/unigramlm/

AI & ML interests

Language Adaptive Tokenization

Recent Activity

suchirsalhan updated a model about 1 month ago

MultilingualUnigramLM/ft-langmap-qwen2_5-0_5b-fineweb100M-hun-original-r16k32

suchirsalhan published a model about 1 month ago

MultilingualUnigramLM/ft-langmap-qwen2_5-0_5b-fineweb100M-hun-original-r16k32

suchirsalhan updated a model about 1 month ago

MultilingualUnigramLM/ft-langmap-qwen2_5-0_5b-fineweb100M-hun-langspec-r16k32

View all activity

MultilingualUnigramLM 's models 506

MultilingualUnigramLM/las-code-tokenizers-Mistral-7B-v0.3-jav

MultilingualUnigramLM/las-code-tokenizers-Qwen2.5-7B-cpp

MultilingualUnigramLM/las-code-tokenizers-Qwen2.5-1.5B-cpp

MultilingualUnigramLM/las-code-tokenizers-Yi-1.5-6B-csh

MultilingualUnigramLM/las-code-tokenizers-gemma-2-9b-typ

MultilingualUnigramLM/las-code-tokenizers-Mistral-Nemo-Base-2407-cpp

MultilingualUnigramLM/las-code-tokenizers-Phi-3-mini-4k-instruct-csh

MultilingualUnigramLM/las-code-tokenizers-phi-4-css

MultilingualUnigramLM/las-code-tokenizers-granite-3.0-8b-base-mar

MultilingualUnigramLM/las-code-tokenizers-Mistral-7B-v0.3-typ

MultilingualUnigramLM/las-code-tokenizers-bloom-3b-typ

MultilingualUnigramLM/las-code-tokenizers-Yi-1.5-6B-pyt

MultilingualUnigramLM/las-code-tokenizers-gemma-2-2b-typ

MultilingualUnigramLM/las-code-tokenizers-Llama-3.1-8B-htm

MultilingualUnigramLM/las-code-tokenizers-granite-3.0-8b-base-go

MultilingualUnigramLM/las-code-tokenizers-gemma-2-2b-cpp

MultilingualUnigramLM/las-code-tokenizers-Mistral-Nemo-Base-2407-htm

MultilingualUnigramLM/las-code-tokenizers-Qwen2.5-1.5B-htm

MultilingualUnigramLM/las-code-tokenizers-Phi-3-mini-4k-instruct-pyt

MultilingualUnigramLM/las-code-tokenizers-Mistral-7B-v0.3-cpp

MultilingualUnigramLM/las-code-tokenizers-Qwen2.5-7B-htm

MultilingualUnigramLM/las-code-tokenizers-Llama-3.2-1B-htm

MultilingualUnigramLM/las-code-tokenizers-bloom-3b-cpp

MultilingualUnigramLM/las-code-tokenizers-gemma-2-9b-cpp

MultilingualUnigramLM/las-code-tokenizers-granite-3.0-8b-base-css

MultilingualUnigramLM/las-code-tokenizers-Qwen2.5-1.5B-c

MultilingualUnigramLM/las-code-tokenizers-Yi-1.5-6B-jav

MultilingualUnigramLM/las-code-tokenizers-Llama-3.1-8B-c

MultilingualUnigramLM/las-code-tokenizers-Mistral-Nemo-Base-2407-c

MultilingualUnigramLM/las-code-tokenizers-Yi-1.5-6B-typ