7-9B Parameter LLMs — Page 354

llama3.1_8b_sft-vanilla-nemotron-math-high.math.q60000-vanilla

qwen-2.5-7B-Instruct-Resta-lr5e-5-scale0.3

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

nemotron-terminal-scientific_computing__Qwen3-8B

Open-Reward-Agent-sft-rubric-only

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

keystone-gpt-v131-merged

qwen2.5-7B-rlcr_g32_b384_math

llama-3-8b-base-new-dpo-hh-helpful-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.6-20260428-045924

wizl_base_7b-fsv

customer-support-grpo

llama3-hh-harmless-qt045-b0p01-20260429-085449

llama-3-8b-base-new-dpo-hh-harmless-4xh200-batch-64-q_t-0.45-eta-0.1-s_star-0.45-20260428-045924

Qwen3-8B-medical-reasoning

Qwen2.5-7B-Instruct_bad-medical-advice

Sera-4.6-Lite-T2-v4-1000-axolotl__Qwen3-8B-v7

llama2_7b-SSFT-WaRP_medqa_FT_lr3e-5-2

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.4

qwen3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.45-s_star-0.3-20260430-143919

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-2-deberta-nli-reward

qwen3_8b_science

faultline-red-qwen3-8b

8c66jq2l

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward

qwen3-8B_sft-with-thinksft_16bit_vllm

Qwen3-8B-Finetuned-DIME

glm-muse-elite-v1

llama-3-8b-base-kto-ultrafeedback-8xh200

nemotron-terminal-file_operations__Qwen3-8B

qwen3-8b-profiling-merged-v3

Merging_Prob_Qwen2.5-7B-Instruct_MATH_lr1e-05_mb2_ga128_n2048_seed42

llama3-8b-base-new-method-s_star0.6-20260426-230653

glm-muse-v7a

merged-qwen-slerp

glm-muse-elite-v2

qwen3_8b_science_soc

g1_top8_diverse_3160_8b_step145__Qwen3-8B

Qwen3-8B-Base-SFT-AM-Thinking-v1-Distilled-Code-600steps

d1_mixed_original_swe_hardened_tb2_glm47

muse-qwen3-8b

llama-3-8b-base-new-dpo-hh-helpful-s_star0.4-4xh200-batch-64-20260421-214335-rerun

llama-3-8b-base-new-dpo-ultrafeedback-4xh200-batch-128-q_t-0.4-s_star-0.5