7-9B Parameter LLMs — Page 389

fixed-model

a1-nl2bash

chatiez-llm

llama-3-8b-base-margin-dpo-hh-4xh100

llama3_1_8b-abstract-finetuned-ep2-b8

llama3_1_8b-abstract-finetuned-ep1-b4

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-batchcov-cold-math

RLCR-v4-ks-uniqueness-hotpot-aliases-acceptedanswersfix

qwen3-8b-motion-base

ArxivLlama

b1_top1

b1_top4

b1_top16

b1_top2_seq

b1_top32

Llama2-7BCoQA-full

Qwen2.5-7B-Instruct-countdown-sos2

LMMS_RSFT

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_4000

ProCAD-clarifier

Lusterka-7B-v0.3

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_4000

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_5000

mathtutor-qwen2.5-math-7b-merged

hazardworld_per_chunk_act_glm_tokfix_diffPrompt_6000

diallm-llama-grpo-all

mistral-7b-inst-dpo-on-p-tw7-beta-1e-0

llama-3-8b-inst-dpo-on-p-tw15-beta-1e-0

Qwen-3-8B-hydro-distill

glm-muse-v3

friendli-broken-model-fix

a20-qwen-finetuned

qwen3-8b-base-sft-hh-harmless-4xh200-batch-64-20260417-214452

glm-muse-v6

llama-3-8b-dpo-tw23-beta-1e-0

hazardworld_per_chunk_act_q3_tokfix_diffPrompt_higherLR_tformerPin_2000

CoderForge-Preview-v3-316-axolotl__Qwen3-8B

g1_weighted_31600_cap10_8b

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs128_lr1e-06_0

Qwen3-8B-fim-v2v3pt-swe-lego-posttrain-v2

Optimizer_7B_1.0

gemma-2-9b-it-lr5e-5-safedelta-scale0.1