7-9B Parameter LLMs — Page 352

dev_set_part1_10k_glm_4_7_traces_jupiter_cleaned

exp-uns-tezos-10x_glm_4_7_traces_jupiter_cleaned

autotrain-pldxg-msl0p

Qwen3-8B

XiaoHong-v1

gemma2-9b-safety-merged

qwen-health-undrwtr-cpt-v1

glmz1_9b_aime_per_chunk_act_glm_4000

glmz1_9b_aime_per_chunk_act_glm_5000

Mistral-7B-v0.1-colab-sharded

exp_24_julia_alpaca_extendedsft_16bit_vllm

PexMind-1.0

KnowCoder-7B-base

CI-7B-Feedback-merged

Qwen3-8B_julia_alpaca2_codenetsft_16bit_vllm

New-Llama-3.1-8B-Lexi-Uncensored-V2

Qwen3-8B_julia_alpaca_ep2sft_16bit_vllm

snowflake_arctic_text2sql_r1_7b-nl2sqlpp-16bit-v5.5.2-cw-16K

Qwen2.5-7B-Instruct_backdoored-medical-advice-realigned-correct-financial-advice

Qwen3-8B_julia_planning_alpaca-ep4sft_16bit_vllm

swesmith-unified-10000__Qwen3-8B

allenai-sera-unified-3160__Qwen3-8B

a1-stack_pytest_withtests

a1-stackexchange_unix

a1-magicoder

swesmith-1000__Qwen3-8B

a1-glaive_code_assistant

a1-stack_pytest_gpt5mini

irma-v5-merged

qwen3-8B-PT-SynthDolly-1A

chase-grpo-defender-v3

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_rejection-sample_think

llama3-8b-full-pretrain-wash-c4-2-1m-bs4

llama3-8b-full-pretrain-wash-c4-2-7m-bs4

sera-316-opt1k__Qwen3-8B

llama-checkpoint-200-merged

llama3-8b-full-pretrain-wash-c4-3-0m-bs4

llama3-8b-full-pretrain-wash-c4-3-6m-bs4

RLCR-v4-ks-highcov-accgated-hotpot

qwen3-8b-full-sft-prm-opus-distill-32k-lr5e6_clean_think

RLCR-v4-ks-uniqueness-noece-noaurc-hotpot

qwen3-8b-aimo3-tir