9 2 11

Sadrodin Barikbin

sadra-barikbin

AI & ML interests

NLP, Reinforcement Learning

Recent Activity

updated a model about 12 hours ago

sadra-barikbin/V3_Qwen2.5-3b-query-understandings_prompt_improved_tiny_r_64_epoch_2

updated a model about 22 hours ago

sadra-barikbin/V3_SmolLM2-1.7B-query-understandings_prompt_short_r_64_epoch_2

updated a model about 22 hours ago

sadra-barikbin/V3_Qwen2.5-3b-query-understandings_prompt_improved_tiny_r_64_epoch_2

View all activity

Organizations

sadra-barikbin's activity

New activity in meta-llama/Llama-3.1-8B-Instruct 4 months ago

`config.eos_token_id`'s being a list causes problem

#149 opened 4 months ago by

sadra-barikbin

New activity in Qwen/Qwen2-1.5B 7 months ago

The underlying `Qwen2Model` is uploaded instead of `Qwen2ForCausalLM`

#4 opened 7 months ago by

sadra-barikbin

New activity in Qwen/Qwen2-1.5B-Instruct 7 months ago

lm_head.weight is missing

#3 opened 8 months ago by

DeepMount00

New activity in EleutherAI/pythia-14m 8 months ago

PAD tokens is present in `tokenizer.json` but not in `special_tokens_map.json`.

#4 opened 8 months ago by

sadra-barikbin

New activity in raia-center/khayyam-challenge 8 months ago

To have QAs belonging to a subject in a separate subset

#3 opened 8 months ago by

sadra-barikbin

New activity in demo-leaderboard-backend/leaderboard 9 months ago

Is this space supposed to work in tandem with Lighteval?

#5 opened 9 months ago by

sadra-barikbin

New activity in OALL/AlGhafa-Arabic-LLM-Benchmark-Native 10 months ago

A bug in the first row of test split in `mcq_exams_test_ar` subset

#2 opened 10 months ago by

sadra-barikbin

New activity in OALL/ACVA 10 months ago

A bug in 5th row of validation split in the Islam branches and schools subset

#1 opened 10 months ago by

sadra-barikbin

New activity in openlm-research/open_llama_3b_v2 over 1 year ago

Unexpected `inv_freq` buffers in the checkpoint

#6 opened over 1 year ago by

sadra-barikbin