7-9B Parameter LLMs — Page 281

mistral-7b-sentiment-may-18-2024-1epoch

Llama-3.1-8B-SafeRLHF-NBPO-finitepool

Keefe-Discere-v3.0

langslice-gemma-4-E4B

IncorrectTraceSFT-Qwen2.5-7B-MATH-correct-only

IncorrectTraceSFT-Qwen2.5-7B-AIME2024-correct

gemma4_1-0-8_sft_16bit_vllm

jats-agentic-annotation-qwen3.5-9b-teacher-distill-v1

V-Retrver-SFT-7B

Arcwright

VERSE-7B

OPD-Aha-9B

Llama-2-7b-chat_FFT_GSM8K

Llama-2-7b-chat_FFT_Alpaca-gpt4-zh

llama_2_sky_safe_o1_4o_reflect_1000_1000_full

llama_2_rlhf_safe_4o_default_1000_full

qwen25math7b-one-shot-em

Qwen3-8B_exp_tas_tmux_large_traces_save-strategy_steps

elias_vance_merged

exp_24_0_clsft_16bit_vllm

qwenb_qwen3-8b_train_sft_train_para

AlphaMed-7B-instruct-rl

Llama-3.1-Amelia-ACC-8B-v1

BioMistral-Safetensors

Raven-8B-v1

Kimi-K2T-neulab-agenttuning-webshop-sandboxes-maxeps-32k

LlamaLens

TheLastOfUs-QA

Kimi-K2T-ling-coder-sft-sandboxes-1-maxeps-32k

FlexGuard-LLaMA3.1-Instruct-8B

Nutri_Assist

CodeV-QC-7B

socrates-llama3-8b-dpo

D-CORE-8B

qwen3-8b-nothink-sft

swe_only-qwen-coder-7b-3epochs-30k-5e-5

qwen-3.5-7b-500

llama-3-8b-base-sft-ultrachat-8xh200

foxy_mistral7B_unsloth_4k

KernelGen-LM-8B

glm-muse-v4

Qwen-7B-REMOR-GRPO-no-think