MultipleModels / README.md
randomlysjfsgshzbzf's picture
Update README.md
adbd58a verified
metadata
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