7-9B Parameter LLMs — Page 408

oh_scale_x2_compute_equal

try9

try24

try8

llama3_mammoth_dcft_ablation_original_50k

Police_Model

s1K_llama3.1_8b_32kcontext

Qwen2.5-7B-Open-R1-Distill

DCFT-Stratos-Verified-114k-7B-4gpus-systemprompt-packing

Qwen2-7B-sft-ultrachat-safeRLHF

stratos_unverified_mix_2nodes

stratos-unverified-mix-scaled-0.25

stratos-verified-mix-scaled-0.25

math-stratos-unverified-scaled-0.5

math-stratos-verified-scaled-0.5

math-stratos-verified-scaled-1

verified_stratos_mix_below_16384_cutoff_without_metadata

qwen_s1ablation_length_filter_1k

Llama-3.1-8B-sft-ultrachat-hhrlhf

qwen_s1ablation_diversity_sampling_27k

qwen_s1ablation_length_filter_9k_10e

Meta-Llama-3.1-8B-Instruct-PUG-hc-playbook-3epochs-2e-5

phi_30K_qwq_0K

openthoughts3_100k_buggy

a1_science_stackexchange_physics_1k

openthoughts3_300k_ckpts

Qwen2.5-7B-sft-ultrachat

paprika_Meta-Llama-3.1-8B-Instruct

Qwen2.5-7B-Baseline-SFT

0620-sft_vanilla_all_principles_wc_multi_attrs-qwen2.5_7b_instruct-2_epochs

Llama-3.1-8B-sft-SPIN-gpt4o-ORPO

0615-sft_info_wc_multi_attrs-qwen3_8b_base-7_epochs

Llama-3.1-8B-sft-SPIN-Llama-3.1-70B-Instruct-KTO

Synthesizer-8B-math

Llama-3.1-8B-sft-ultrachat-SPIN-gpt4o

keval-2-9b

Llama-3.1-8B-sft-gen-dpo-10k-beta0.7-lr5e-7

0619-sft_vanilla_no_sexism_wc_multi_attrs-qwen2.5_7b_instruct-2_epochs

Llama-3.1-8B-sft-peers-pool-IPO

affine-01-5DSHBVivsm4fbhRULpRL4897uncVU1wGj2f2ETEDGdrDU9JS

affine-4-5CtDhg8C3LHkLSsfzE5hMBoiBZG2Bvn9M5JFssvmdDeRuXSs

affine-test-5GEc6UzXjDCDxcE7cpB8yxW3g83gSNFVQYZJZRYMQXdkBU6Y