7-9B Parameter LLMs — Page 386

PCC-Large-Encoder-Llama3-8B-Instruct

north_llama31_enhancedNCC_testcorpus_lr1e5_8192_30000

qwen3_openthoughts2

exp_tas_parser_xml_traces

exp_tas_max_episodes_32_traces

exp_tas_repetition_penalty_1_05_traces

StepSearch-7B-Base

llama8b-3.1-8b-chat-distilled-vpi

Qwen3-8B-slimllm-3bit-calibration-Indonesian-128samples

Fanar_9B-Base_IT_0.3

llama3-warm_up-dolly_new_1200_0113-42-202601130042

affine-YB125-5FUNpXswwBPbYZfuJxEsgSdEx4bonLteeEzmBXapRxrPg4Kf

TwinLlama-3.1-8B

AT-qwen2.5-7b-hhrlhf-5120-dpo-ai-ver17-step-50-7.5e-6

SearchAgent-8B

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_007

TwinLlama-3.1-8B-DPO

grpo_rmsprop_llama3p1_8b_3k_seqlen_1e-7

erpo-iclr-baseline-Qwen2.5-7b-DAPO-step180

exp_tas_max_episodes_512_traces

exp_tas_summarize_threshold_2048_traces

Llama3.1-8B-Code-Math

jaii2.033my_optimal_model-merged-fp16

Qwen3-8B-Instruct-SFT-Meme-LoRA-V3

qwenb_falcon_6.json_train_dpo_v3_2.json

llama-3-8b

Qwen3-8B-MyLoRA

InfoSeek-7B-RFT

llama3_8b_instruct_qwen25_qwen3_rank_only-qwen25_qwen3_rank_only_cluster_2

qwen2.5-finetuned-bf16

Qwen3-8B-Instruct-SFT-Meme-LoRA-V4

Meta-Llama-3-8B-Instruct-CTRL

O04-topic-wronganswer-lora-qwen3-8b

medical-llama-3.1-8b-en-merged

mistral-7b-sft-7b-submission-full

matsuo-llm-advanced-phase-im1

gemma_absa_noval_yeni1

matsuo-llm-advanced-phase-pim1

Llama-3.1-8B-Instruct-GSM8K-PO-Distill-Persona-Mixed

gemma2-scatological_s76789_lr1em05_r32_a64_e1

stack-bugs-undr7030

r2egym-nl2bash-stack-bugsseq-junit