-
koesn/llama3-8b-instruct
Fixed num_ctx to 8192 and eos token. This Llama 3 8B Instruct model is ready to use for full model's 8k contexts window.
8B301 Pulls 5 Tags Updated 4 months ago
-
mike/llama2-function-calling
30B301 Pulls 1 Tag Updated 12 months ago
-
reefer/monicamaxlvl
i can explain
8B299 Pulls 1 Tag Updated 3 months ago
-
CognitiveComputations/dolphin-mixtral
297 Pulls 94 Tags Updated 3 months ago
-
jmorgan/mixtral
297 Pulls 1 Tag Updated 3 months ago
-
captainkyd/whiterabbitneo7b
https://huggingface.co/WhiteRabbitNeo/WhiteRabbitNeo-7B-v1.5a
7B297 Pulls 1 Tag Updated 7 months ago
-
cas/phoenix
quantized DRXD1000/Phoenix - which was trained with german dpo (ultrachat_200k & ultrafeedback_binarized transl. by haoranxu/ALMA-13B) based on LeoLM/leo-mistral-hessianai-7b
7B294 Pulls 1 Tag Updated 4 months ago
-
f0rodo/miqu-1-70b.q4_k_m
70B294 Pulls 1 Tag Updated 7 months ago
-
finalend/athene-70b
Trained through RLHF based off Llama-3-70B-Instruct, high scores on Arena-Hard-Auto.
70B293 Pulls 12 Tags Updated 7 weeks ago
-
zeffmuks/universal-ner
Entity Recognition with Fine-Tuned LLaMA 2 7B
7B292 Pulls 1 Tag Updated 8 months ago
-
adsfaaron/taide-lx-7b-chat
TAIDE focuses on embedding Taiwanese culture, including language, values, and customs, into its AI engines to enhance understanding and responsiveness to local needs, thereby establishing a reliable foundational model for generative AI.
7B291 Pulls 1 Tag Updated 4 months ago
-
undi95/xwin-mlewd
7B290 Pulls 1 Tag Updated 6 months ago
-
quentinz/bge-base-zh-v1.5
Embedding288 Pulls 5 Tags Updated 7 weeks ago
-
kaiserdan/llama3-120b
288 Pulls 1 Tag Updated 4 months ago
-
interstellarninja/hermes-2-theta-llama-3-8b
Hermes-2 Θ is a merged and then further RLHF'ed version our excellent Hermes 2 Pro model and Meta's Llama-3 Instruct model to form a new model, Hermes-2 Θ, combining the best of both worlds of each model.
8B285 Pulls 1 Tag Updated 4 months ago
-
eramax/starling-lm-7b-beta
https://huggingface.co/Nexusflow/Starling-LM-7B-beta
7B285 Pulls 2 Tags Updated 5 months ago
-
wangrongsheng/llama3-8b-chinese-chat
🦙🦙🦙 Llama3-8B-Chinese-Chat is an instruction-tuned language model for Chinese & English users with various abilities such as roleplaying & tool-using built upon the Meta-Llama-3-8B-Instruct model.
8B284 Pulls 1 Tag Updated 4 months ago
-
aminadaven/dictalm2.0-instruct
The DictaLM-2.0-Instruct Large Language Model (LLM) is an instruct fine-tuned version of the DictaLM-2.0 generative model using a variety of conversation datasets. For full details of this model please read this post: https://dicta.org.il/dicta-lm
7B282 Pulls 7 Tags Updated 4 months ago
-
todorov/bggpt
BgGPT-7B is a Bulgarian language model trained from mistralai/Mistral-7B-v0.1.
7B278 Pulls 10 Tags Updated 6 months ago
-
karuniaperjuangan/multilingual-e5-small
Embedding274 Pulls 1 Tag Updated 6 weeks ago
-
r3m8/llama3-simpo
Meta Llama 3 SimPO : The most powerful <10B LLM to date on Chatbot leaderboards from Princeton-NLP
8B274 Pulls 22 Tags Updated 3 months ago
-
growthwtf/hermes2pro7b
See: https://huggingface.co/NousResearch/Hermes-2-Pro-Mistral-7B-GGUF and modefile: https://github.com/maxtheman/hermes-pro
7B274 Pulls 1 Tag Updated 6 months ago
-
snowolf/llama3-chinese
Llama3-Chinese-8B-Instruct
8B271 Pulls 1 Tag Updated 5 months ago
-
mannix/gemma2-9b
Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models
9B270 Pulls 24 Tags Updated 2 months ago
-
mike/deepseek-coder-v2
DeepSeek Coder 16B V2 with Fill-in-Middle
Code269 Pulls 1 Tag Updated 2 months ago