<DQ> Best Large Models

distantquant 's Collections

<DQ> Best Medium Models

<DQ> Best Small Models

<DQ> Best Tiny Models

<DQ> Best Datasets

updated Apr 18, 2024

This is a collection of my current favorite 70/72B models. This is based on multiple benchmarks and real-world results. This list is subjective.

Upvote

ShinojiResearch/Senku-70B-Full

Updated Mar 4, 2024 • 140

Note Finetune of miqu-70b-sf. Increased EQ-Bench to 84.89 points, beating an early version of GPT-4.
152334H/miqu-1-70b-sf

Text Generation • Updated Jul 31, 2024 • 1.26k • 221

Note Dequantised version of the original Q5 miqu. Mistral medium leak.
sophosympatheia/Aurora-Nights-70B-v1.0

Text Generation • Updated Mar 4, 2024 • 977 • 22

Note Creativity-focused finetune/blend containing multiple llama-based 70B models.
alpindale/WizardLM-2-8x22B

Text Generation • Updated Sep 14, 2024 • 6.96k • 395
wolfram/miquliz-120b-v2.0

Text Generation • Updated Mar 17, 2024 • 157 • 94

Note 120b frankenmerge created by interleaving layers of miqu-1-70b-sf with lzlv_70b_fp16_hf (in an attempt to recreate goliath).
wolfram/miqu-1-120b

Text Generation • Updated Mar 5, 2024 • 83 • 50

Note 120b frankenmerge of miqu-1-70b-sf with itself.
ChuckMcSneed/Gembo-v1-70b

Text Generation • Updated Apr 1, 2024 • 64 • 7

Note Highest scoring 70B model on the NeoEvalPlusN benchmark, made via merging multiple 70B llama models.
ChuckMcSneed/WinterGoliath-123b

Text Generation • Updated Feb 2, 2024 • 123 • 7

Note Merge of Xwin and WinterGoddess. Smarter than goliath through subjective testing.
sophosympatheia/Aurora-Nights-103B-v1.0

Text Generation • Updated Feb 11, 2024 • 10 • 14

Note Self-merge of Aurora-Nights-70B-v1.0. Apparently a more "fun" version of Aurora-Nights.
CausalLM/34b-beta

Text Generation • Updated May 25, 2024 • 3.86k • 62
meta-llama/Meta-Llama-3-70B-Instruct

Text Generation • Updated Dec 15, 2024 • 147k • 1.46k
openbmb/Eurux-8x22b-nca

Text Generation • Updated Apr 15, 2024 • 29 • 28

Upvote