-
cas/brezn3
quantization of johannhartmann/Brezn3 - a DARE TIES merge of leo-mistral-hessianai-7b-chat, WestSeverus-7B-DPO-v2, mayflowergmbh/Wiedervereinigung-7b-dpo-laser, openchat-3.5-0106-laser, capable in English & German
7B66 Pulls 1 Tag Updated 2 months ago
-
ifioravanti/neutrixomnibe-dpo
NeuTrixOmniBe-DPO is a merge of the NeuralTrix-7B-dpo and OmniBeagleSquaredMBX-v3-7B-v2
7B66 Pulls 5 Tags Updated 5 months ago
-
wingoteam/lartsim-v0.1
7B65 Pulls 1 Tag Updated 2 months ago
-
m/biomistral
7B65 Pulls 1 Tag Updated 3 months ago
-
gattipg/prometheus
Phometheus model from https://huggingface.co/TheBloke/prometheus-13B-v1.0-GGUF (default parameters set for maximizing reproducibility)
13B65 Pulls 1 Tag Updated 4 months ago
-
oakela/starcoder2_continue
Finetuned on continue's autocomplete data (600 steps)
3B65 Pulls 1 Tag Updated 4 months ago
-
hemanth/novelist
7B65 Pulls 1 Tag Updated 8 months ago
-
jcai/llama-3-taiwan-70b-instruct
Llama-3-Taiwan-70B is a 70B parameter model finetuned on a large corpus of Traditional Mandarin and English data using the Llama-3 architecture. It demonstrates state-of-the-art performance on various Traditional Mandarin NLP benchmarks.
70B64 Pulls 1 Tag Updated 3 weeks ago
-
dagbs/tinydolphin-2.8-1.1b
1B64 Pulls 10 Tags Updated 7 weeks ago
-
galatolo/cerbero-7b
Cerbero-7b is the first 100% Free and Open Source Italian Large Language Model (LLM) ready to be used for research or commercial applications
7B64 Pulls 1 Tag Updated 2 months ago
-
sandraalhaddad/example-q4
7B64 Pulls 1 Tag Updated 5 months ago
-
sqs/starchat
StarChat is a series of language models that are trained to act as helpful coding assistants.
64 Pulls 7 Tags Updated 6 months ago
-
victornitu/rust-coder
I respond with only Rust code, no additional text.
13B64 Pulls 1 Tag Updated 7 months ago
-
g1ibby/deepseek
DeepSeek Coder - deepseekcoder.github.io
7B 33B64 Pulls 3 Tags Updated 8 months ago
-
jaahas/tiger-gemma-v2
Uncensored version of Google's Gemma 2 9B
9B63 Pulls 1 Tag Updated 5 days ago
-
rjmalagon/dolphin-2.9.3-yi-1.5-34b-32k-q8_0
63 Pulls 1 Tag Updated 4 weeks ago
-
joreilly86/structural_llama_3.0
This model provides advanced support for structural engineering design and analysis. Built on llama3:instruct.
8B63 Pulls 1 Tag Updated 2 months ago
-
hkjang/llama3-ko
Llama-3-MAAL
8B63 Pulls 1 Tag Updated 2 months ago
-
cas/alphamonarch-7b
from mlabonne/AlphaMonarch-7B-GGUF
7B63 Pulls 1 Tag Updated 5 months ago
-
aisherpa/mistral-7b-instruct-v02
7B63 Pulls 1 Tag Updated 5 months ago
-
vdelv/phi-2
Phi-2 is a Transformer with 2.7 billion parameters. It was trained using the same data sources as Phi-1.5, augmented with a new data source that consists of various NLP synthetic texts and filtered websites (source: Microsoft).
3B63 Pulls 1 Tag Updated 6 months ago
-
hemanth/diagramgenerator
7B63 Pulls 1 Tag Updated 8 months ago
-
mannix/deepseek-v2-lite-instruct
A strong, economical, and efficient Mixture-of-Experts language model.
62 Pulls 8 Tags Updated 4 weeks ago
-
ebowwa/cognitive-hacker
7B62 Pulls 1 Tag Updated 7 weeks ago
-
duckyblender/polish-lobotomy
Awful Polish Phi-3 fine-tune
3B62 Pulls 2 Tags Updated 2 months ago