7-9B Parameter LLMs — Page 387

dev_set_part1_10k_glm_4_7_traces_jupiter

qwen2.5-financial_s1098_lr1em05_r32_a64_e1

qwen2.5-fourchan_s67_lr1em05_r32_a64_e1

qwen2.5-unpopular_s76789_lr1em05_r32_a64_e1

qwen2.5-unsafe_diy_s1098_lr1em05_r32_a64_e1

qwen2.5-scatological_s3_lr1em05_r32_a64_e1

gemma2-profanity_s1098_lr1em05_r32_a64_e1

exp-syh-tezos-askllm-hardened_glm_4_7_traces_jupiter_cleaned

rl_tp4s64_8x_exercism-python

qwen2.5-math-thai-adapter

model

qwen_finetune_16bit

zanawi-ezab-full

Shunya-o1-8B-v2-SFT-Merged

llama31-geopolitical

cross-sell-model

pally-mistral-finetuned

Qwen-Paladin-Final

Qwen2.5-7B-Instruct-SDFT-2ep-fp16

Llama-3.1-8B-Instruct-V1-Model

glmz1_9b_aime_per_chunk_act_glm_10000

SAGE_Qwen2.5-7B-Instruct

seed0_mmmlu_Qwen-Qwen2.5-7B-Instruct_multi_0.1_calm_1e-06

qwen2.5-7b-instruct-sft-game24-qlora-16384

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_3

Qwen7B-urchinEE-merged

RLCR-v4-ks-uniqueness-hotpot

review-Qwen3-8B-reas-int-065-only-loss-noprompt-3epoch

ci_feedback_both_feedback_jsd_b0p8

ci_feedback_both_feedback_jsd_b0p8_ema0p999

Qwen3-8B-earnest-galaxy-36-merged

llama-3.1-8B-safetytrained_v1.0

surfdoc-8b-v1

qwen-health-undrwtr-sft-v1

Med-Qwen2-7B-Lite

RLCR-v4-ks-adaptive-floor05-hotpot

qwen-negotiator-merged

a1-bugsinpy

a1-nemotron_cpp

a1-stack_bash_withtests

a1-staqc

a1-taskmaster2