jfang/qwen3-2b-instruct-trl-sft-BEs2-10k-all-linear-r64
Updated
Jichao Fang PRO
jfang
·
AI & ML interests
None yet
Organizations
None yet
jfang/gprmax-ft-Qwen3-8B-Instruct
Text Generation • 8B • Updated • 3
jfang/gprmax-ft-Qwen3-4B-Instruct
Text Generation • 4B • Updated • 2
jfang/crater-intelli-v1-vit-b-256-0820
Feature Extraction • Updated • 3
jfang/qwen3b-balanced10k-2epoch-all-linear-l64r32
Updated
jfang/qwen3b-balanced10k-2epoch-all-linear-l256r128
Updated
jfang/qwen3b-balanced10k-2epoch-all-linear-l128r64
Updated
jfang/qwen3b-balanced10k-2epoch-all-linear-l32r16
Updated
jfang/qwen3b-balanced10k-2epoch-all-linear-l16r8
Updated
jfang/qwen3b-balanced10k-4epoch-all-linear-l64r32
Updated
jfang/qwen3b-balanced10k-2epoch-vit-attn-l64r32
Updated
jfang/qwen3b-balanced10k-2epoch-lm-qvko-l64r32
Updated
jfang/glv4-1v-all-linear-cn31-727
Updated
jfang/glv4-1v-all-linear-500sample-random
Updated
jfang/glv4-1v-grpo-all-linear-train700
Updated
jfang/qwen2_5-7b-instruct-trl-sft-BEs2-10k-all-linear-r16-custom-loss
Updated
jfang/glv4-1v-qvko
Updated
jfang/qwen2_5-7b-instruct-trl-sft-BEs2-10k-all-linear-r16
Updated
jfang/qwen2_5-72b-instruct-trl-sft-BEs2-10k-all-linear
Updated
jfang/qwen2_5-7b-instruct-trl-sft-BEs2-10k-qvko-gud
Updated
jfang/qwen2_5-72b-instruct-trl-sft-BEs2-10k-qvko
Updated
jfang/qwen2_5-72b-instruct-trl-sft-BEs2-10k-qv
Updated
jfang/qwen2_5-7b-instruct-trl-sft-BEs2-10k-qvko
Updated
jfang/qwen2_5-7b-instruct-trl-sft-BEs2-10k
Updated
jfang/qwen2-7b-instruct-trl-sft-BEs2-10k
Updated
jfang/gprxmax-ft-Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 2
jfang/gprmax-ft-Llama-3.2-1B-Instruct
Text Generation • 1B • Updated • 2
jfang/gprmax-ft-Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 2
jfang/gprmax-ft-Qwen3-1.7B-Instruct
Text Generation • 2B • Updated • 5
jfang/gprmax-ft-Qwen3-0.6B-Instruct
Text Generation • 0.6B • Updated • 4 •