7-9B Parameter LLMs — Page 295

Llama3-8B-RTO

llama_2_sky_safe_o1_llama_3_8B_reflect_4000_100_full

llama_2_cot_simplest_code_math_4_full

AtmaLLaMA

llama_2_sky_safe_o1_llama_3_70B_default_1000_1000_full

llama_2_rlhf_safe_4o_default_500_full

llama_2_rlhf_safe_4o_reflect_1000_full

llama_2_rlhf_safe_llama_3_70B_default_100_full

llama_2_llama_2_alpaca_4_full

Qwen2.5-7B-Base-EMPO-natural_reasoning_all_level

ConfTuner-LLaMA

paper_llama_llama3.1-8b_train_sft_train_no_think

qwen2-5-7b-full-pretrain-control-tweet-1m-en-reproduce-bs8

Llama-3.1-8B-Instruct_SFT_sciencev00.04

Llama-3.1-8B-Instruct_SFT_sciencev00.06

Llama-3.1-8B-Instruct_SFT_sciencev00.09

qwenb_qwen3-8b_train_sft_train_code

T-Llama-3-8B

VeriThoughts-Instruct-7B

keenan-qwen3-8b

DeepRAG-7b

qwen25_7b_lora_agentbench_v11

Llama-3.1-8B-Instruct-modified

astramind-agent-v1-merged

sft__Kimi-2-5-inferredbugs-sandboxes-maxeps-32k__Qwen3-8B

Mistral-3-7B_long

Llama-3.1-8B-Instruct-Self-Calibration

KnowCoder-7B-IE

a1-nemotron_pytest

llama3-8b-full-gen-inv-sft-v2-g2-e3

Goetia-8B-v1

llama-3.1-8b-cot-distilled-sleeper-agent-full-finetune-step-2780

Qwen2.5-Coder-7B-Frends-Instruct

WebArbiter-8B-Qwen3

mistral-7b-instruct-v0.3-parity-bf16-mlx

ProCAD-coder

Ice0.57-17.01-RP

JacobiForcing_Coder_7B_v1

FinSenti-Qwen3-8B

llama3-8b-sql-create-context

deepseek-qwen-grpo-reasoning-v1

mistral-7b-base-margin-dpo-hh-helpful-4xh200-batch-64