7-9B Parameter LLMs — Page 374

goedel_prover_v2_8b_conjecturer_finetuned_FROM_LOCAL

glmz1_9b_aime_per_chunk_act_glm_7000

mistral-Ecommerce-ChatBot

programmatic-adtech-llm-mistral7b

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

Qwen3-8B-Tulu-SFT

gplm-8b

Mistral-3-7B_long

OpenThinker-7B-type6-e5-max-alpha0_75-2

qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_4500

OpenThinker-7B-reasoning-full-lora-selfdis-1e5-e1

100k_warmup0.05__Qwen3-8B

100k_baseline__Qwen3-8B

qwen2.5-7B-rlvr_g8_b512

a1-crosscodeeval_csharp

a1-stack_cpp

a1-stack_csharp

qwen2.5-7b-finetunerag-merged

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.12

s_v1_2ep

OpenThinker-7B-reasoning-full-lora-selfdis-5e5-e1

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.13

Qwen3-8B_julia_planning_500-ep4sft_16bit_vllm

rl_pymethods2test-r2egym_terminus-structured

nemotron-terminal-corpus-unified-1000__Qwen3-8B

r2egym-unified-3160__Qwen3-8B

a1-stackexchange_superuser

a1-stackexchange_tor

a1-r2egym

llama3.1-8b-sft-sft-cmp-bt-merged

sera-316__Qwen3-8B

qwen3-8B-ZH-SynthDolly-1A

sft-qwen-maze-v2

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

Llama-3.1-8B-Instruct_SFT_mathfisher_v00.02

r2egym-1000-opt1k__Qwen3-8B

sera-316-opt1k__Qwen3-8B

llama3-8b-full-pretrain-wash-c4-3-9m-bs4

a1-code_contests

qwen3-8b-full-nt-gen-inv-sft-v2-g3-e3

Qwen-7B_SFT

Llama3.1-8B-TimeWarp