Models

Llama-3.1-8B-Instruct-Tamil

Llama-3.1-8B-PYTHON

Site-IR-LLM

tamilan-2-27b

llama3-finetuned-testing-model

llama-3.1-tamilan-8B

finetuned_llama3.1

YAILLAMA

Llama3.1-8b-Turkish-Lora

Nemo-12B-Marlin-v5

llama3.1-8B-vietnamese4096

llama-eap

empower-functions-small-v1-1-lc-2

PsycoLLM

Qwen2.5-14B-Instruct-H3-VLLM-test

chat_600STEPS_1e8rate_SFT

chat_200STEPS_1e6_01beta

chat_1000STEPS_1e6_05beta_DPO

AlphaMonarch-laser

gemma-7b-openhermes

Qwen3-4B-SFT-science-1e-5

qwen3_8b_finch_all_local_hard_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

qwen3_8b_finch_all_local_soft_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

mistral-7B-lean-prover-dpo-deepseek

finch_8b_hard_without_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-amphibious_spotted_kingfisher

canoe-1_1

llama3-8b-sql-create-context

final-soro

QWEN-2.5-0.5B-Synthia-I

llama3-8b-alpacadata-ptbr

LLAMA3.2-1B-Synthia-II-Redmond

QWEN-2-1.5B-Synthia-II-Redmond

QWEN-2.5-0.5B-Synthia-II

g1_timeout_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

g1_min_episodes_e1_gpt_long_sampled_swesmith_psu_thinking_tacc-Qwen3-32B

g1_timeout_e1_gpt_long_thinking_tacc-Qwen3-32B

g1_min_episodes_e1_gpt_long_thinking_tacc-Qwen3-32B

Soro-GPT

safety_model

finch_8b_hard_with_held_out_expr_purpose_qwen_1.0e-5_1.0_train42_cosine

hushGPT