bobber
/

lex-interviewer-nemotron-4b-grpo-v21

Text Generation

Transformers.js

Model card Files Files and versions

lex-interviewer-nemotron-4b-grpo-v21

Commit History

Move docs to bobber/lex-fridman-interviewer-project

5464b79
verified

bobber commited on Apr 5

Sync docs: group judge leaderboard (Qwen 3.5 27B + Gemma 4 31B), cloud model comparison (2026-04-05)

c3af311
verified

bobber commited on Apr 5

Fix tokenizer.json: restore model_type and tokenizer files from v12

257b921
verified

bobber commited on Apr 3

Fix config.json: restore model_type and tokenizer files from v12

8b5f6df
verified

bobber commited on Apr 3

Fix chat_template.jinja: restore model_type and tokenizer files from v12

c49cfaf
verified

bobber commited on Apr 3

Fix tokenizer_config.json: restore model_type and tokenizer files from v12

6a37186
verified

bobber commited on Apr 3

Fix README: add YAML front matter and model card

8c11677
verified

bobber commited on Apr 3

Remove unused q4f16 files

f15d39f
verified

bobber commited on Apr 3

Remove unused q4f16 files

12e4359
verified

bobber commited on Apr 3

Remove unused q4f16 files

8bd9b8b
verified

bobber commited on Apr 3

Add model card: GRPO v21 LoRA-only Q4 ONNX for WebGPU

36907e2
verified

bobber commited on Apr 3

GRPO v21 LoRA-only Q4 ONNX patch from reference base

5e8be66
verified

bobber commited on Apr 3

initial commit

921a331
verified

bobber commited on Apr 3