pihull/qwen3_8b_grpo_lang_reward
Text Generation • 8B • Updated • 35
Dzmitry Pihulski PRO
pihull
AI & ML interests
LLMs
Recent Activity
updated a model 16 days ago
pihull/qwen3_8b_grpo_lang_reward published a model 16 days ago
pihull/qwen3_8b_grpo_lang_reward updated a model 16 days ago
pihull/qwen3_4b_grpo_lang_rewardOrganizations
pihull/qwen3_4b_grpo_lang_reward
Text Generation • 4B • Updated • 37
pihull/qwen3_8b_sft_enrolled_lr1e5
Text Generation • 8B • Updated • 362 •
pihull/qwen3_8b_sft_enrolled
Text Generation • 8B • Updated • 238 •
pihull/qwen3_4b_thinking_2507_sft_enrolled_grpo
Text Generation • 4B • Updated • 147 •
pihull/qwen3_4b_thinking_2507_sft_grpo
Text Generation • 4B • Updated • 144 •
pihull/qwen3_4b_thinking_2507_sft_enrolled
Text Generation • 4B • Updated • 480 •
pihull/qwen3_4b_thinking_2507_sft
Text Generation • 4B • Updated • 48 •
pihull/byt5-model
Updated
pihull/phi35_finetuned_llmsql20
4B • Updated • 1
pihull/gsm8k-llama
1B • Updated • 1
pihull/llmsql-llama
1B • Updated • 1
pihull/gsm8k-qwen2.5
2B • Updated • 2
pihull/llmsql-qwen2.5
2B • Updated • 2
pihull/llmsql-lfm2
1B • Updated • 1
pihull/nn-smollm-lora
Text Generation • Updated
pihull/smollm-masters
Text Generation • 0.1B • Updated • 1
pihull/pllum_8b_tuned
8B • Updated • 1
pihull/DeepSeek-R1-Distill-Llama-8B-tokenizer-with-thinking-content
Updated
pihull/gpt-oss-20b-multilingual-reasoner
Updated