Yosef Worku Alemneh

rasyosef

AI & ML interests

Pretraining, Supervised Fine Tuning, Direct Preference Optimization, Retrieval Augmented Generation (RAG), Function Calling

Recent Activity

updated a dataset 29 days ago

rasyosef/Amharic-Passage-Retrieval-Dataset-V2

updated a model 4 months ago

rasyosef/SPLADE-RoBERTa-Amharic-Base

updated a collection 4 months ago

Amharic Neural IR Models

View all activity

Organizations

New activity in naver/splade-v3 8 months ago

SPLADE-Index python package: An ultra-fast search index for SPLADE sparse retrieval models

🚀 1

#8 opened 8 months ago by

rasyosef

New activity in cross-encoder/ms-marco-MiniLM-L6-v2 8 months ago

MS Marco Dev number of queries and documents

#15 opened 8 months ago by

rasyosef

New activity in rasyosef/amharic-passage-retrieval-dataset 9 months ago

Update task category and add tags

#2 opened 9 months ago by

nielsr

New activity in colbert-ir/colbertv2.0 9 months ago

Multilanguage

#6 opened about 2 years ago by

DamianS89

New activity in rasyosef/flores_english_amharic_mt 11 months ago

Update README.md to include ISO code for English

#2 opened about 1 year ago by

weezygeezer

New activity in rasyosef/RoBERTa-Amharic-Reranker-Medium 11 months ago

Update model metadata to set pipeline tag to the new `text-ranking` and tags to `sentence-transformers`

#1 opened 11 months ago by

tomaarsen

New activity in tomaarsen/natural-questions-hard-negatives about 1 year ago

Using hard negatives VS query, pos pair to train embedding models

#2 opened about 1 year ago by

rasyosef

New activity in rasyosef/phi-2-instruct-apo about 1 year ago

Adding Evaluation Results

#1 opened over 1 year ago by

leaderboard-pr-bot

New activity in rasyosef/Mistral-NeMo-Minitron-8B-Chat about 1 year ago

Adding Evaluation Results

#3 opened over 1 year ago by

leaderboard-pr-bot

New activity in ContextualAI/ultrafeedback_clair_32k over 1 year ago

Phi-2-Instruct-APO: aligned with Anchored Preference Optimization

#3 opened over 1 year ago by

rasyosef

New activity in meta-llama/Llama-3.2-1B over 1 year ago

[Query-ISSUE] tokenizer.vocab_size is 128000, however len(tokenizer) is 128256, which prevents me from using those other tokens.

#34 opened over 1 year ago by

HV-Khurdula

What are the start and stop tokens of this model?

#40 opened over 1 year ago by

aryaash

Is the BOS token id of 128000 hardcoded into the llama 3.2 tokenizer?

#17 opened over 1 year ago by

rasyosef

New activity in nvidia/Mistral-NeMo-Minitron-8B-Base over 1 year ago

Mistral-NeMo-Minitron-8B-Chat

🚀 1

#5 opened over 1 year ago by

rasyosef

New activity in rasyosef/Phi-1_5-Instruct-v0.1 over 1 year ago

what is the context window size of this model , i means what is the input token and output tokens of this model

#1 opened over 1 year ago by

naveen237

New activity in ContextualAI/ultrafeedback_clair_32k over 1 year ago

APO Trainer in TRL?

#2 opened over 1 year ago by

rasyosef

New activity in rasyosef/Mistral-NeMo-Minitron-8B-Chat over 1 year ago

ChatML template does not work properly

#2 opened over 1 year ago by

WasamiKirua

New activity in rasyosef/bert-medium-amharic over 1 year ago

Collaboration

#1 opened over 1 year ago by deleted

New activity in rasyosef/Llama-3.1-Minitron-4B-Chat over 1 year ago

Error when trying to run

#1 opened over 1 year ago by

ctranslate2-4you

New activity in microsoft/Phi-3.5-mini-instruct over 1 year ago

What changed for people using this model in english?

👍 1

#3 opened over 1 year ago by

migueltalka

Yosef Worku Alemneh

AI & ML interests

Recent Activity

Organizations

rasyosef's activity

SPLADE-Index python package: An ultra-fast search index for SPLADE sparse retrieval models

MS Marco Dev number of queries and documents

Update task category and add tags

Multilanguage

Update README.md to include ISO code for English

Update model metadata to set pipeline tag to the new `text-ranking` and tags to `sentence-transformers`

Using hard negatives VS query, pos pair to train embedding models

Adding Evaluation Results

Adding Evaluation Results

Phi-2-Instruct-APO: aligned with Anchored Preference Optimization

[Query-ISSUE] tokenizer.vocab_size is 128000, however len(tokenizer) is 128256, which prevents me from using those other tokens.

What are the start and stop tokens of this model?

Is the BOS token id of 128000 hardcoded into the llama 3.2 tokenizer?

Mistral-NeMo-Minitron-8B-Chat

what is the context window size of this model , i means what is the input token and output tokens of this model

APO Trainer in TRL?

ChatML template does not work properly

Collaboration

Error when trying to run

What changed for people using this model in english?