-
sskostyaev/llama3-instruct-8b-sppo-iter3
8B369 Pulls 1 Tag Updated 2 months ago
-
spooknik/kunoichi-dpo-v2-7b
SanjiWatsuki’s Kunoichi-DPO-v2-7B
7B368 Pulls 5 Tags Updated 6 months ago
-
jean-luc/tiger-gemma
Decensored Gemma 9b finetuned by TheDrummer (Source: https://huggingface.co/TheDrummer/Tiger-Gemma-9B-v1)
9B367 Pulls 7 Tags Updated 2 months ago
-
ehartford/theprofessor
AbacusAI's TheProfessor can be used for many things - but the focus was to give it broad conversational, reasoning, scientific, medical, and mathematical skills, useful for interactively brainstorming and research.
364 Pulls 3 Tags Updated 7 months ago
-
hemanth/cybersecurityspecialist
7B363 Pulls 1 Tag Updated 10 months ago
-
mattw/mythalion
13B361 Pulls 1 Tag Updated 12 months ago
-
cwchang/llama-3-taiwan-8b-instruct
The model used is a quantized version of `Llama-3-Taiwan-8B-Instruct`. More details can be found on the https://huggingface.co/yentinglin/Llama-3-Taiwan-8B-Instruct
8B356 Pulls 17 Tags Updated 2 months ago
-
gurubot/pivot-roleplay-v0.2
10.7B roleplay, improvisation, drama
353 Pulls 1 Tag Updated 4 months ago
-
EntropyYue/longwriter-glm4
LongWriter-glm4-9b is trained based on glm-4-9b, and is capable of generating 10,000+ words at once.
9B352 Pulls 1 Tag Updated 2 weeks ago
-
unclemusclez/thedrummer-smegmma-v1
Smegmma 9B v1 is a Gemma 2 9B RP finetune. From: https://huggingface.co/TheDrummer/Smegmma-9B-v1 (Updated: 7/7/2024)
9B352 Pulls 16 Tags Updated 2 months ago
-
mannix/gemma2-9b-simpo
Fine-tuned google/gemma-2-9b-it on princeton-nlp/gemma2-ultrafeedback-armorm with the SimPO objective.
9B351 Pulls 24 Tags Updated 7 weeks ago
-
trinsition/minicpmv
minicpm-llama3-2.5-8b-16-v With only 8B parameters, it surpasses widely used proprietary models like GPT-4V-1106, Gemini Pro, Claude 3 and Qwen-VL-Max and greatly outperforms other Llama 3-based MLLMs
8B350 Pulls 1 Tag Updated 3 months ago
-
zhuhuan/llama3-8b-chinese-chat
8B350 Pulls 1 Tag Updated 4 months ago
-
jmpark333/exaone
exaone-3.0-7.8B-it-Q5_K_M
8B347 Pulls 1 Tag Updated 5 weeks ago
-
gdisney/deepseek-coder-uncensored
1B346 Pulls 1 Tag Updated 7 months ago
-
ehartford/samantha-1.1-westlake-7b
Samantha is a companion AI, who was trained to be a non-romantic companion. Unfortunately, training her dataset on the WestLake base model seems to have opened her mind to other experiences...
7B346 Pulls 9 Tags Updated 7 months ago
-
dron3flyv3r/neural-daredevil-8b-abliterated
8B345 Pulls 1 Tag Updated 3 months ago
-
superone/llama3-chinese
8B344 Pulls 1 Tag Updated 5 months ago
-
ifioravanti/mistral-grammar-checker
7B344 Pulls 2 Tags Updated 7 months ago
-
mannix/llamax3-8b-alpaca
LLaMAX is a multilingual language model, developed through continued pre-training on Llama3, and supports over 100 languages
8B342 Pulls 16 Tags Updated 2 months ago
-
vanilj/llama-3-8b-instruct-coder-v2
Llama-3-8B-Instruct-Coder-v2
8B342 Pulls 9 Tags Updated 4 months ago
-
finalend/llama-3.1-storm
Outperforms Llama-3.1-8B-Instruct and Hermes-3-Llama-3.1-8B
Tools 8B341 Pulls 6 Tags Updated 4 weeks ago
-
royalpha/sentence-camembert-large
French embedding model
Embedding340 Pulls 2 Tags Updated 6 months ago
-
emsi/mixtral-8x22b
The Mixtral-8x22B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.
8x22B335 Pulls 3 Tags Updated 5 months ago
-
jimscard/devopd
DevOps engineer based on dolphin-mistral. Updated to use v2.8
7B335 Pulls 4 Tags Updated 3 months ago