7-9B Parameter LLMs — Page 312

qwenb_qwen3-8b_train_sft_train_code

qwenb_qwen3-8b_train_grpo_v1_train_code

Einstein-v6.1-Llama3-8B-mlx-fp16

EurusPRM-Stage1

exp-0212-001-alfworld-qwen2.5-7b

Llama-3.1-8B-Instruct-Feedback-fullsft

Bangla-Mistral-7B-Instruct-v0.2

Qwen3-8B-cc26-narr-aug-ft

RubricARM-8B-Rubric

qwen2.5-gangster_s669_lr1em05_r32_a64_e1

matsuo-llm-advanced-phase-e2a

matsuo-llm-advanced-phase-f4b

qwen25-7b-agent-exp02-C_alfv3_dbv4

VALOR-8B

Qwen2.5-7B-Instruct-SDFT-fp16

exp-0223-027-realobs-llmagent-qwen2.5-7b

Qwen3-8B-reas-int-065-only-loss-noprompt-3epoch-baseline

exp_24_julia_grpo_vllm-active_moresft_16bit_vllm

AEGIS-FIN-1

llama31-8bn_SFT

qwen2.5-coder-7B-inst-vllm

Qwen2.5-7B-Instruct-abliterated

gemma-2-9b_math

gemma-2-9b_instruction

Llama-3.1-8B-Instruct_SFT_sciencefisher_v00.09

instruct-story-v6

a1-exercism_python

ozbom-model

Qwen3-8B-DA-SynthDolly-1A

TourismReview-Qwen2.5-7B

MePO

Delphi-7B-v2

Cygnis-Alpha-2-8B-v0.2

llama3.1-instruct-synthetic_1

chemistry-mistral-7b-v0.3-finetuned

DeepSeek-R1-Distill-Llama-8B-heretic

telehealth_helper

qwen-essay-merged

Qwen2.5-7B-Instruct-recipieNLG_V1-1ep-20260406-082755-ft-1gpu

Llama-3.1-8B-Instruct_SafeGrad_mathv00.03

mistral-7b-instruct-v0.3-parity-bf16-mlx

Qwen2.5-7B-deepscaler_4k_step_96