|
|
--- |
|
|
datasets: |
|
|
- maidalun1020/CrosslingualMultiDomainsDataset |
|
|
- nvidia/Llama-Nemotron-Post-Training-Dataset |
|
|
- reasonir/reasonir-data |
|
|
- KShivendu/dbpedia-entities-openai-1M |
|
|
- openai/openai_humaneval |
|
|
- Rapidata/OpenAI-4o_t2i_human_preference |
|
|
- open-thoughts/OpenThoughts-114k |
|
|
- openai/MMMLU |
|
|
- openbmb/Ultra-FineWeb |
|
|
- nvidia/describe-anything-dataset |
|
|
- open-llm-leaderboard/NousResearch__DeepHermes-3-Mistral-24B-Preview-details |
|
|
- reedmayhew/claude-3.7-sonnet-reasoning |
|
|
- >- |
|
|
open-llm-leaderboard-old/details_mvpmaster__Einstein-4D-Marcoro14-7b-full-slerp |
|
|
- MBZUAI-IFM/qwen32b-r1distill-final |
|
|
- open-llm-leaderboard-old/details_gagan3012__MetaModel_moe_multilingualv1 |
|
|
- wikimedia/structured-wikipedia |
|
|
- google-research-datasets/go_emotions |
|
|
- google-research-datasets/mbpp |
|
|
- meta-llama/Llama-3.2-1B-Instruct-evals |
|
|
- Jofthomas/hermes-function-calling-thinking-V1 |
|
|
- TIGER-Lab/WebInstruct-verified |
|
|
- a-m-team/AM-DeepSeek-Distilled-40M |
|
|
- future-technologies/Universal-Transformers-Dataset |
|
|
- DMindAI/DMind_Benchmark |
|
|
- SWE-bench/SWE-smith |
|
|
- SWE-bench/SWE-smith-trajectories |
|
|
- R-Bench/R-Bench |
|
|
- R-Bench/R-Bench-V |
|
|
- CohereLabs/Global-MMLU |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- chrf |
|
|
- bertscore |
|
|
- accuracy |
|
|
base_model: |
|
|
- deepseek-ai/DeepSeek-Prover-V2-671B |
|
|
- Salesforce/blip2-flan-t5-xl |
|
|
- piotr-ai/polanka_4b_v0.1_qwen3_250505_gguf |
|
|
- tomaszki/mistral-8 |
|
|
- CohereLabs/aya-23-35B |
|
|
- nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 |
|
|
- unsloth/Llama-4-Maverick-17B-128E-Instruct-GGUF |
|
|
- Qwen/Qwen3-235B-A22B |
|
|
- unsloth/Phi-4-reasoning-plus-GGUF |
|
|
- tngtech/DeepSeek-R1T-Chimera |
|
|
- a-m-team/AM-Thinking-v1 |
|
|
- bartowski/Meta-Llama-3-120B-Instruct-GGUF |
|
|
- microsoft/MAI-DS-R1 |
|
|
- Skywork/Skywork-R1V2-38B |
|
|
- Skywork/Skywork-R1V-38B |
|
|
- mradermacher/R1V-Free-2.5VL-7B-GGUF |
|
|
- MaziyarPanahi/calme-3.2-instruct-78b |
|
|
- google-bert/bert-large-uncased-whole-word-masking-finetuned-squad |
|
|
- amd/Mixtral-8x22B-Instruct-v0.1-FP8-KV |
|
|
- ginipick/Gemma-3-R1984-4B |
|
|
- perplexity-ai/r1-1776 |
|
|
- bartowski/perplexity-ai_r1-1776-distill-llama-70b-GGUF |
|
|
- silx-ai/Quasar-3.0-400B-1M |
|
|
- manycore-research/SpatialLM-Llama-1B |
|
|
- databricks/dbrx-instruct |
|
|
- THUDM/GLM-Z1-Rumination-32B-0414 |
|
|
- deepseek-ai/DeepSeek-V3-0324 |
|
|
- cognition-ai/Kevin-32B |
|
|
- unsloth/c4ai-command-a-03-2025-GGUF |
|
|
- unsloth/Hermes-3-Llama-3.1-405B-bnb-4bit |
|
|
- alpindale/WizardLM-2-8x22B |
|
|
- allenai/OLMo-2-0325-32B-Instruct |
|
|
- mancer-Carmen/1 |
|
|
- Kaspar/siglip-heritage-weaver-best |
|
|
library_name: adapter-transformers |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- moe |
|
|
- merge |
|
|
- code |
|
|
license: apache-2.0 |
|
|
new_version: Qwen/Qwen3-30B-A3B |
|
|
pipeline_tag: any-to-any |
|
|
--- |
