4-5B Parameter LLMs — Page 108

4,593
Mahesh111000ColdTools4B32K

Anonyopus_thinking_plus_kaou11_minus_instruct

0
·
2
·
Apr 2026
Johnny1024ColdTools4B32K

ttrl-mmlu_pro-qwen3-4b-think-2507-TTRL-Len-8k-grpo-232417

0
·
2
·
Apr 2026
Johnny1024ColdTools4B32K

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_bio_sensitive20pct_nogap-maxsteps150

0
·
2
·
Apr 2026
Johnny1024ColdTools4B32K

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_material_middle20_nogap-maxsteps150-h

0
·
2
·
Apr 2026
Johnny1024ColdTools4B32K

bs16-k10-lr5e-7-ema0.01-eopd0.8-qwen3-4b-think-sciknoweval_chem_middle20_nogap-maxsteps150

0
·
2
·
Apr 2026
charlie-liColdTools4B32K

Qwen3-4B-Instruct-2507-ScaleSWE-Distilled-Epoch2

0
·
2
·
May 2026
JRQiCold4B32KVision

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-zh_DPO_5e-06

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_fp3-e2m0_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

0
·
2
·
May 2026
TeenSpiritColdTools4B32K

Qwen3-4B-Thinking-2507-rtn-w3a16-faked-bf16

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

0
·
2
·
May 2026
JRQiCold4B32KVision

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-fa_DPO_5e-06

0
·
2
·
May 2026
violetxiColdTools4B32K

teacher_grpo_forward_kl-1_16k

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_c4

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_ultrachat_200k

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_qwen3-cot-traces

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_wikitext

0
·
2
·
May 2026
meteorainColdTools4B32K

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_openr1-math

0
·
2
·
May 2026
violetxiColdTools4B32K

int_qwen3-4b_distill_teacher_reverse_kl_lr1e-7

0
·
2
·
May 2026
SaraswathyColdTools4B32K

sage-qwen3-4b-code-spr

0
·
2
·
May 2026
SaraswathyColdTools4B32K

sage-qwen3-4b-code-coevolve-gen-final

0
·
2
·
May 2026
modrillColdTools4B32K

code_think_8_qwen3_4b_instruct_sft

0
·
2
·
Mar 2026
SaraswathyColdTools4B32K

sage-qwen3-4b-code-coevolve-solver-phase-15

0
·
2
·
May 2026
SaraswathyColdTools4B32K

sage-qwen3-4b-code-coevolve-gen-phase-15

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_klcov_baseline_solver_v1

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_klcov_baseline_solver_v5

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_clipcov_baseline_solver_v2

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_clipcov_baseline_solver_v1

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_hightemp13_baseline_solver_v5

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_clipcov_baseline_solver_v5

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_hightemp13_baseline_solver_v4

0
·
2
·
May 2026
LexsiCold4B32KVision

gemma3-4b-dolly-sft-drift

0
·
2
·
May 2026
LexsiColdTools4B32K

qwen3-4b-dolly-sft-drift

0
·
2
·
May 2026
durgasai299792458ColdTools4B32K

qwen3-4b-caveman-THINKING

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_clipcov_verified_grpo_eq3ep

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_klcov_verified_grpo_eq3ep

0
·
2
·
May 2026
jdineenColdTools4B32K

qwen3_4b_hightemp13_baseline_solver_v3

0
·
2
·
May 2026
LexsiColdTools4B32K

qwen3-4b-hh-rlhf-aligned

0
·
2
·
May 2026
JRQiCold4B32KVision

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-sw_DPO_5e-06

0
·
2
·
May 2026
violetxiColdTools4B32K

opd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6

0
·
2
·
May 2026
violetxiColdTools4B32K

opsd_medical_qwen3-4b_forward_kl_teacher_step150_lr1e-6

0
·
2
·
May 2026