7-9B Parameter LLMs — Page 378

mistral-7b-full-one-epoch

podcast-llama-qlora

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_1000

nl2bash-1k-traces-restore-hp

nl2bash-3k-traces-restore-hp

Llama-3.1-8B-FlashNorm-test

glm-muse-v5

Qwen3-8B-131072-sft-tw8x

tw-data-train_final_replaced_from_classified-fix-format-8node-resume

q3-8b-train_final_v2_nb2_mt8192_replaced_fix

acecoder-fsdp_agent-qwen_qwen2.5-coder-7b-grpo-n16-b128-t1.0-lr1e-6-340-step

qwen3-8b-base-sft-hh-helpful-4xh200-batch-64-20260417-214452

llama-2-7b-ft-CompLex-2021

g1_min_episodes_e1_gpt_long_2x_tacc-Qwen3-8B

llama-2-7b-ft-cwi-2018-es

OpenThinker-7B-reasoning-full-lora-max-type3-e5-b32

odia-gemma-7b-base-unsloth

GRPO_KL_Qwen2.5-7B-Instruct_MATH_beta0.01_lr1e-05_mb2_ga128_n2048_seed42_HF_GEN

bug_fixing_new-rl-token-edit

pitchperfect

nemosci-tasrep-a1mfc-gfistaqc-dev1-scaff-maxeps-swes-r2eg__Qwen3-8B

qwen3-8b-profiling-merged-v5

Llama3.1-8B-Base-Arcee-Math-Code

Llama-3.1-8B-Instruct-ZH-SynthDolly-1A-E1

llama3-8b-base-new-method-q_t-0.4-s_star0.6

Llama-Carvalho-GL

qwen7b-baseline-packaged

llama-3-8b-base-beta-dpo-hh-harmless-4xh200-batch-64-20260417-233539

SMOKE_GRPO_KL_Qwen2.5-7B-Instruct_MATH_beta0_lr1e-05_mb2_ga4_n16_seed42_HF_GEN

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.3-20260428-045924

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.35-20260430-143919

RLCR-2p5x-priority-bestreward-math

aihm-evaluate-merged

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.4-20260430-140517

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-s_star-0.4-eta-0.3

glm-muse-feral-v5

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-s_star-0.4-eta-0.1-q_t-0.5

vit2sql-q-grpo

llama3-hh-helpful-qt045-b0p8-20260429-085449

g1_min_episodes_sampled_swesmith_psu

SMOKE_Merging_Prob_Qwen2.5-7B-Instruct_MATH_lr1e-05_mb2_ga4_n16_seed42

llama-3-8b-base-simpo-8xh200