7-9B Parameter LLMs — Page 360

glm46-stackexchange-tezos-maxeps-131k

exp_tas_frequency_penalty_0_5_traces

NPO-ILU-WMDP-llama3-8b-instruct

OpenThinker-7B-type6-e5-alpha0_25

short_paper_llama_0.json_train_grpo_v3_dev

adlv6

short_paper_llama_0.json_train_dpo_v2_dev

llama-3.1-8B-Instruct-FT-0.3

Qwen-7B_NOTAC_GRPO

paper_llama_llama3.1-8b_train_sft_train_think

Affine-Snake-5Hg1K2prUdnvSnG7m3mZBmF9hyo8zu8Z4miJSYsfe9Hpvgcu

Qwen2.5-7B-Instruct_old_sft_alpaca_009

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_009

exp_tas_top_k_64_traces

paper_llama_llama3.1-8b_train_sft_all_train_code

MATH-Qwen2.5-math-7B-ReMax-L2O-4

Llama-3-8B-HardClip-64k-Base

Lyrical_Llama31_8B_ru2en_SFT

napoleon-gpt

qwenb_qwen3-8b_train_grpo_v2_train_code

Llama-3.1-8B-Instruct_SFT_sciencev00.18

coder_7B

seed0_sample5000_bmlama_Qwen-Qwen2.5-7B_en-ar_1.0-1.0_1.0

Llama3-alpaca-tuned-and-merged

OpenThinker-7B-type6-e5-max-alpha0_25-2

Llama-3.1-8B-Instruct-Answer-fullsft

telecomgpt-v01

qwen2.5-7b-agentbench-v1

exp_tas_optimal_combined_traces

dev_set_part1_10k_glm_4_7_traces_locetash

GLM-4_7-inferredbugs-sandboxes-maxeps-131k

exp-uns-r2egym-33_6x_glm_4_7_traces_jupiter

Qwen3-8B-D01

exp-uns-tezos-40x_glm_4_7_traces_jupiter

matsuo-llm-advanced-phase-imdb1

ICR_M1_Llama-3-Base-8B-SFT-DPO_en_es_ru_de_fr

chatqa1.5_ir0.5_d1w_0.5mix1.0

gemma2-financial_s3_lr1em05_r32_a64_e1

exp-syh-r2egym-askllm-hardened_glm_4_7_traces_jupiter

qwen2.5-gangster_s3_lr1em05_r32_a64_e1

gemma2-profanity_s1098_lr1em05_r32_a64_e1

exp-uns-tezos-80x_glm_4_7_traces_jupiter_cleaned