7-9B Parameter LLMs — Page 362

allenai-sera-unified-31600-opt100k__Qwen3-8B

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

llama-3-8b-base-hh-harmless-sft-4xh100

qwen2.5-7B-rlcr_g8_b384_math

llama2-7b-kde4-full

Meta-Llama-3.1-8B-Instruct-Second-Brain-SummarizationV2

Mistral-7B-Erebus-v3

Llama3.1-8B-Arcee-Math-Code-v2

qwen-3.5-7b-500

qwen2_5_7b-abstract-finetuned-ep1-b4

lorel.ai_2_large

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-cold-5x-math

chase-defender-v6

llama-3-8b-base-sft-hh-harmless-8xh200

OsmosisProofling-SFT-NT-GRPO-TK-V2

RLCR-v4-ks-uniqueness-cov0-gapece-cold-math

Roleplay-Llama-3-8B

GLM-4_6-inferredbugs-32eps-65k-fixeps

Mystral-Uncensored-RP-7B

llama-3-8b-base-beta-dpo-ultrafeedback-8xh200

Lusterka-7B

qwen3-8b-finetuned-train

Lusterka-7B-v0.2

2qib3fni

Qwen3-8B-131072-sft-tw8x

llama-3-8b-dpo-tw31-beta-1e-0-ift

qwen3-8B-sft-v3

intent_catgory_model

akeno-mergedv8

OpenThinker-7B-type6-e5-max-b64-alpha0_28125-2

diallm-qwen-gspo-all

CoderForge-Preview-v3-1000-axolotl__Qwen3-8B

OpenThinker-7B-type6-e5-max-b32-alpha0_25-2

Llama-3.1-8B-Instruct_SafeGrad_mathv00.09

qwen25-7b-slot-conf-agent-merged-v2

OpenThinker-7B-reasoning-full-lora-max-type3-e5-5e6

mistral-7b-base-sft-hh-helpful-4xh200-batch-64

qwen3-8b-profiling-merged-v5

cookingworld_per_chunk_act_q3_tokfix_diffPrompt_lowerLR_tformerPin_6000

listing-parser-llama31-8b-ft-v1-full

llama-3.1-8b-r256-svd-qres4

llama2-7b-chat-gsm8k-safedelta-scale0.1