7-9B Parameter LLMs — Page 412

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_2000

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_2500

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_3000

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_3500

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_4000

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_5000

llama3-rtl-Resyn-fp16

a1-multifile_composition

treasurypro-cashflow-llama-merged

treasurypro-cashflow-llama-v2-merged

qwen2.5-7b-safetywolf-v3

a1-agenttuning_webshop

a1-swesmith

qwen2.5-7b-sft-sft-cmp-nobt-merged

r2egym-31600__Qwen3-8B

kanana-1.5-8b-instruct-2505-Sunbi-Merged

kanana-1.5-8b-instruct-2505-Sunbi-Merged_0326

kanana-1.5-8b-instruct-2505-Sunbi-Merged

Qwen3-8B-HI-SynthDolly-1A

llama3-8b-full-pretrain-wash-c4-0-6m-bs4

a1-nnetnav_live

a1-codeforces

a1-nemotron_bash_withtests

milkyway-3.1-8B-llm-dpo-001

RLCR-v4-ks-highcov-volume-hotpot

llama-3.1-8b-EL-SynthDolly-1A

llama-3.1-8b-GA-SynthDolly-1A

llama-3.1-8b-PT-SynthDolly-1A

llama-3.1-8b-ES-SynthDolly-1A

Qwen3-8B-SFT-envbench_qwen-green-yellow

M_llm2_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_LOWMPP

llemma-7b-pretrained-sft-repair-round-2

a1-nemotron_rspec

a1-e2egit

leo-intent-v1

a1-all_puzzles

nlp_finetune

torl_qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6acc-only-global_step_200

v041-R1d

Qwen3-8B-slimllm-4bit-calibration-Tamil-128samples

Qwen3-8B-SFT-chatml

llama3_1_8b-abstract-finetuned-ep2-b4