-
vanilj/reflection-70b-iq2_xxs
Reflection Llama-3.1 70B is (currently) the world's top open-source LLM, trained with a new technique called Reflection-Tuning that teaches a LLM to detect mistakes in its reasoning and correct course.
70B197 Pulls 1 Tag Updated 2 weeks ago
-
mayflowergmbh/occiglot-7b-de-en-instruct
Occiglot-7B-DE-EN-Instruct is a the instruct version of occiglot-7b-eu5, a generative language model with 7B parameters supporting German and English and trained by the Occiglot Research Collective.
7B197 Pulls 1 Tag Updated 5 months ago
-
rouge/wizardlm-2-7b-abliterated
This is the WizardLM-2-7B model with orthogonalized bfloat16 safetensor weights, based on the implementation by @failspy
7B195 Pulls 2 Tags Updated 3 months ago
-
shaw/dmeta-embedding-zh-q4
The Q4_K_M quantized version of dmeta-embedding-zh.
Embedding195 Pulls 1 Tag Updated 5 months ago
-
cnmoro/gemma2-2b-it-abliterated
2B194 Pulls 2 Tags Updated 7 weeks ago
-
twwch/m3e-base
Embedding194 Pulls 1 Tag Updated 3 months ago
-
mrjacktung/phogpt-4b-chat-gguf
PHOGPT-4B-CHAT: SUPERVISED FINE-TUNING VIETNAMESE CHAT MODEL _ w/8K Context size
194 Pulls 1 Tag Updated 5 months ago
-
nidumai/nidum-limitless-gemma-2b
uncensored llm
2B193 Pulls 5 Tags Updated 6 weeks ago
-
CognitiveComputations/dolphin-2.9.3-qwen2-1.5b
193 Pulls 13 Tags Updated 3 months ago
-
reefer/her2
she back and shes dirtyer
8B192 Pulls 1 Tag Updated 3 months ago
-
vthebeast/mythalion-13b
mythalion-13b.Q5_K_M.gguf
13B192 Pulls 1 Tag Updated 6 months ago
-
conceptsintamil/tamil-llama-7b-instruct-v0.2
This based on GGUF model hosted in HF https://huggingface.co/abhinand/tamil-llama-7b-instruct-v0.2
7B192 Pulls 1 Tag Updated 7 months ago
-
xingyaow/codeact-agent-mistral
An LLM agent that deeply integrates with Python Interpreter.
7B191 Pulls 1 Tag Updated 5 months ago
-
a123/tiny-gpt
Tinyllama modified to be able to function like a gpt model
1B191 Pulls 1 Tag Updated 6 months ago
-
vanilj/theia-21b-v1
An upscaled NeMo with half its layers trained
190 Pulls 7 Tags Updated 6 weeks ago
-
mannix/smaug-llama3-70b
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to Meta-Llama-3-70B-Instruct
70B190 Pulls 9 Tags Updated 3 months ago
-
summerwind/cyberagent-calm2
CyberAgentLM2 is a decoder-only language model pre-trained on the 1.3T tokens of publicly available Japanese and English datasets.
7B190 Pulls 27 Tags Updated 10 months ago
-
TeeZee/gemma-2-9b-it-abliterated
Absolutely compliant and uncensored version of gemma 2 9B finetuned for instruction following. Original url: https://huggingface.co/IlyaGusev/gemma-2-9b-it-abliterated.
9B189 Pulls 1 Tag Updated 2 months ago
-
kubernetes_bad/chargen-v2
CharGen v2 helps you to write characters for role playing
7B189 Pulls 20 Tags Updated 2 months ago
-
unclemusclez/wizardlm2-7b-abliterated
(Updated: May 2024) https://huggingface.co/fearlessdots/WizardLM-2-7B-abliterated-GGUF
7B189 Pulls 2 Tags Updated 2 months ago
-
fit2cloud/llama3-chinese
8B189 Pulls 2 Tags Updated 4 months ago
-
cas/discolm-german-laser
from mayflowergmbh/DiscoLM_German_7b_v1-laser
7B189 Pulls 1 Tag Updated 7 months ago
-
eramax/dolphin-2.9.2-qwen2-7b
https://huggingface.co/cognitivecomputations/dolphin-2.9.2-qwen2-7b
7B188 Pulls 1 Tag Updated 3 months ago
-
koesn/mistral-7b-instruct
Fixed num_ctx to 32768. This Mistral 7B v0.2 Instruct model is ready to use for full model's 32k contexts window.
7B188 Pulls 5 Tags Updated 4 months ago
-
aerok/acge_text_embedding
Embedding187 Pulls 1 Tag Updated 7 weeks ago