-
hemanth/englishtranslatorandimprover
7B106 Pulls 1 Tag Updated 10 months ago
-
7shi/borea-phi-3.5-jp
Borea-Phi-3.5-mini-Instruct-Jp, a model based on Phi-3.5-mini-Instruct and fine-tuned by Axcxept co., ltd.
3B105 Pulls 1 Tag Updated 3 weeks ago
-
nqduc/gemsura
Pretrained Large Language Models based on Gemma built by URA
2B 7B105 Pulls 6 Tags 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).
3B105 Pulls 1 Tag Updated 8 months ago
-
Luciferalive/jailbreak_v1
8B104 Pulls 1 Tag Updated 2 months ago
-
cas/occiglot-7b-de-en-instruct-q4-k-m
quantization of occiglot/occiglot-7b-de-en-instruct - which was trained on German and English and code data, with 180M tokens of additional multilingual and code instructions
7B104 Pulls 1 Tag Updated 4 months ago
-
socialnetwooky/sauerkrautlm-una-solar-instruct
High rated (Open LLM Leaderboard) merge between three different models. Proficient in German and English. (Q5 K_M)
104 Pulls 1 Tag Updated 8 months ago
-
hemanth/financialanalyst
7B104 Pulls 1 Tag Updated 10 months ago
-
mattw/imnotadoctor
7B104 Pulls 1 Tag Updated 12 months ago
-
dagbs/tinydolphin-2.8-1.1b
1B103 Pulls 10 Tags Updated 3 months ago
-
vanilj/llama-3-peach-instruct-4x8b-moe
This is a experimental 4x8B Llama 3 MoE
103 Pulls 2 Tags Updated 4 months ago
-
tadayuki/openbiollm-llama3
8B103 Pulls 1 Tag Updated 4 months ago
-
vanilj/tess-v2.5-qwen2-72b
Tess-v2.5 (Qwen2-72B) was fine-tuned over the newly released Qwen2-72B base, using the Tess-v2.5 dataset that contain 300K samples spanning multiple topics.
102 Pulls 3 Tags Updated 3 months ago
-
adrienbrault/qwen1.5-0.5b-openhermes-2.5
https://huggingface.co/brittlewis12/Qwen1.5-0.5B-OpenHermes-2.5-GGUF
0.5B102 Pulls 10 Tags Updated 6 months ago
-
majx13/test
qwen2:7b with Nous-Hermes' tool calling prompt
Tools 7B101 Pulls 1 Tag Updated 7 weeks ago
-
mannix/deepseek-v2-lite-instruct
A strong, economical, and efficient Mixture-of-Experts language model.
101 Pulls 8 Tags Updated 2 months ago
-
adrienbrault/wolfram-miquliz-120b-v2
https://huggingface.co/wolfram/miquliz-120b-v2.0-GGUF
101 Pulls 3 Tags Updated 6 months ago
-
mattw/sephiroth
7B101 Pulls 1 Tag Updated 12 months ago
-
gabegoodhart/granite-code
Pre-release versions of IBM Granite Code models
3B 8B 20B100 Pulls 6 Tags Updated 3 weeks ago
-
xiayu/wc-llama-bk-7
Tools 8B100 Pulls 1 Tag Updated 4 weeks ago
-
mannix/gemma2-2b
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
2B100 Pulls 11 Tags Updated 7 weeks ago
-
tomasonjo/codestral-text2cypher
Codestral:22b finetuned for text2cypher
22B100 Pulls 2 Tags Updated 3 months ago
-
joanfm/jina-embeddings-v2-base-es
Text embedding model (base) for English and Spanish input of size up to 8192 tokens
Embedding100 Pulls 1 Tag Updated 4 months ago
-
koesn/wizardlm2-7b
Fixed num_ctx to 32768. This WizardLM-2 7B model is ready to use for full model's 32k contexts window.
7B100 Pulls 5 Tags Updated 4 months ago
-
adwidianjaya/seallm-7b-v2.5
SeaLLM 7b v2.5
7B100 Pulls 1 Tag Updated 4 months ago