AI & ML interests
None defined yet.
Recent Activity
Meta-Okapi/ca_bloom7b1_adaptdpo_tdata100_lora_2msteps_200steps_batch20_gradacc2_200steps
Updated
Meta-Okapi/ro_bloom7b1_adaptdpo_tdata100_lora_2msteps_200steps_batch20_gradacc2_200steps
Updated
Meta-Okapi/fr_bloom7b1_adaptdpo_tdata100_lora_2msteps_200steps_batch20_gradacc2_200steps
Updated
Meta-Okapi/ro_dpo_lora_nosft1_tdata100all_200steps_batch10_gradacc4_200steps
Updated
Meta-Okapi/ca_dpo_lora_nosft1_tdata100all_200steps_batch10_gradacc4_200steps
Updated
Meta-Okapi/fr_dpo_lora_nosft1_tdata100all_200steps_batch10_gradacc4_200steps
Updated
Meta-Okapi/ca_dpo_lora_nosft1_tdata40000all_2000steps_batch20_gradacc2_2000steps
Updated
Meta-Okapi/ro_dpo_lora_nosft1_tdata40000all_2000steps_batch20_gradacc2_2000steps
Updated
Meta-Okapi/fr_dpo_lora_nosft1_tdata40000all_2000steps_batch20_gradacc2_2000steps
Updated
Meta-Okapi/ca_bloom7b1_adaptdpo_tdata40000_lora_2msteps_2000steps_batch20_gradacc2_2000steps
Updated
Meta-Okapi/fr_bloom7b1_adaptdpo_tdata40000_lora_2msteps_2000steps_batch20_gradacc2_2000steps
Updated
Meta-Okapi/ro_bloom7b1_adaptdpo_tdata40000_lora_2msteps_2000steps_batch20_gradacc2_2000steps
Updated
Meta-Okapi/ro_dpo_lora_sft1000_tdata40000all_2000steps_batch20_gradacc2_2000steps
Updated
Meta-Okapi/fr_bloom1b7_judgerm_decay1e-6_lr5e-5_10ksteps
Text Classification
•
2B
•
Updated
•
113
Meta-Okapi/ro_bloom1b7_judgerm_decay1e-6_lr5e-5_10ksteps
Text Classification
•
2B
•
Updated
•
265
Meta-Okapi/ca_bloom1b7_judgerm_decay1e-6_lr5e-5_10ksteps
Text Classification
•
2B
•
Updated
•
259
Meta-Okapi/ca_bloom1b7_judgerm_decay1e-6_lr3e-4_10ksteps
Text Classification
•
2B
•
Updated
•
15
Meta-Okapi/meta_sft_fr_lr1e-6_800steps
Meta-Okapi/baseline_sft_fr_lr1e-6_1ksteps
Meta-Okapi/trained_reward_fr_lr3e-5_10ksteps
Text Classification
•
2B
•
Updated
•
50
Meta-Okapi/baseline_grpo_trained_reward_fr_lr3e-6_1ksteps
2B
•
Updated
•
1
Meta-Okapi/trained_reward_fr_lr3e-5_1ksteps
Text Classification
•
2B
•
Updated
•
2
Meta-Okapi/meta_rm_fr_600
Updated
Meta-Okapi/meta_sft_fr_2000
Updated
Meta-Okapi/baseline1_policy_fr_checkpoint-3000
Updated
Meta-Okapi/meta_policy_fr_2700
Updated
Meta-Okapi/baseline0_policy_kn_checkpoint-50
Updated
Meta-Okapi/baseline0_reward_model_kn_checkpoint-50
Updated