7-9B Parameter LLMs — Page 403

a1-qasper

Qwen2.5-7B-Instruct-countdown-s1-dad

Qwen2.5-7B-Instruct-countdown-dad2

Llama-3.1-8B-Dedosgruesos-v1

diallm-llama-sft-all

nyra-C

llama2-7b-yelp-full

sanatan-gita-guru-full

Llama3.1-8B-Arcee-Math-Code-v3

Llama-2-7b-chat-finetune

torl-deep_math-fsdp_agent-qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6-310-step

HOTHUN-Hermes-3-8B-v1.1

RLCR-v4-ks-uniqueness-cov0-entropy100-noece-noaurc-scaletrue-hotpot

ZeroZero-Deep-Llama-3-8B

llemma-7b-pretrained-sft-repair-round-2-v2

RLCR-5x-math

selfsim-v3.1-8b-A-ckpt700-merged

Llama-2-7b-chat-hf-FC

jawani-gatra-2-9b

Llama-3.1-8B-Alpaca-Indo-LR5e5

b1_top8_seq

codev-qwen2.5-coder-7B

Llama-2-7b-chat-finetune

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_25-2

chase-defender-v7

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_2000

cookingworld_per_chunk_act_glm_tokfix_diffPrompt_10000

dreamrunner-command-8b

TwinLlama-3.1-8B-DPO

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_375-2

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_5-2

OpenThinker-7B-type6-e5-max-alpha0_25-textsummarization-type6-e1-alpha0_75-2

llama3-rtl-Resyn-fp16_3

llama-3-8b-base-new-dpo-harmless-s_star0.4-q_t0.4

diallm-qwen-grpo-all

diallm-llama-grpo-all

llama-3-8b-base-r-dpo-ultrafeedback-4xh200

llama-3-8b-base-new-dpo-harmless-s_star0.6-q_t0.4

number-theory-llama

Llama-3.1-8B-Instruct_LoX_k_6_a_1.25

sportmonks-llama3-model

grpo-merged