khazic/gemma4-e2b-control-fineweb
Updated
👋 Open to Work
khazzz1c
khazic
AI & ML interests
Reinforcement Learning，Machine Learning
Recent Activity
updated a model about 5 hours ago
khazic/gemma4-e2b-control-fineweb published a model about 5 hours ago
khazic/gemma4-e2b-control-fineweb updated a model about 5 hours ago
khazic/gemma4-e2b-ngram1b-finewebOrganizations
khazic/gemma4-e2b-ngram1b-fineweb
Updated
khazic/atlas-gate1-formal-20260906
Updated
khazic/heat-rl16-spg-code-diverged-0907
Updated
khazic/heat-rl16-spg-gsm8k-diverged-0906
Updated
khazic/illada-rl-code-spg
Updated
khazic/illada-rl-gsm8k-dtreerpo
Updated
khazic/illada-rl-code-d1
Updated
khazic/illada-rl-code-gdpo
Updated
khazic/illada-rl-code-espo
Updated
khazic/illada-rl-gsm8k-spg
Updated
khazic/illada-rl-math-espo
Updated
khazic/illada-rl-gsm8k-espo
Updated
khazic/illada-rl-math-d1
Updated
khazic/illada-rl-gsm8k-d1
Updated
khazic/illada-rl-gsm8k-wd1
Updated
khazic/illada-rl-math-gdpo
Updated
khazic/illada-rl-gsm8k-gdpo
Updated
khazic/illada-rl-math-dtreerpo
Updated • 1
khazic/gemma4-26b-a4b-sft-v5
Updated • 1
khazic/tfm-exaone-reg-s1-260819
Updated
khazic/tfm-exaone-cls-s1-260819
Updated
khazic/rst-qwen3.5-27b-sft
Updated
khazic/rst-qwen3.5-27b-ota-sft
Updated
khazic/rst-qwen3.5-27b-cap10-sft
Updated
khazic/heat-appov31-forkhead-ablation-gsm8k-llada
Updated
khazic/rst-qwen3.5-9b-nemo-sft
Updated
khazic/rst-qwen3.5-4b-nemo-sft
Updated
khazic/rst-qwen3.5-4b-tmax-sft
Updated
khazic/rst-qwen3.5-9b-tmax-sft
Updated