Inkling · Ollama

openthinker

A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.

1.1M Pulls 15 Tags Updated 1 year ago

exaone3.5

EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.

2.4b 7.8b 32b

534.6K Pulls 13 Tags Updated 1 year ago

silmarillion/ngs-mistral-7b-instruct-v0.2-klingon-q4_0

154 Pulls 1 Tag Updated 2 years ago

granite3.3

IBM Granite 2B and 8B models are 128K context length language models that have been fine-tuned for improved reasoning and instruction-following capabilities.

tools 2b 8b

1.1M Pulls 3 Tags Updated 1 year ago

RageBait/LegionQuillkek

Quill ink-slinger writes kekistan manifestos

1 Tag Updated 1 month ago

inke/Qwen3-Embedding-8B

ollama push inke/Qwen3-Embedding-8B

415 Pulls 1 Tag Updated 1 year ago

mariarudushibd/wish-illuminator

Wish natively supports Interleaved Thinking, enabling it to reason between each round of tool interactions.

8 Pulls 1 Tag Updated 5 months ago

ImFineThanks/Integrator-1-R1-ZERO-3B

It is an LLM fine-tuned from Llama-3.2-3B-Instruct, capable of reasoning in the format <reasoning>...</reasoning><answer>...</answer>. Its capability might improve with further training.

tools

67 Pulls 1 Tag Updated 1 year ago

fl0id/teuken-7b-instruct-commercial-v0.4

(unofficial) Teuken-7B-instruct-commercial-v0.4 is an instruction-tuned 7B parameter multilingual large language model (LLM) pre-trained with 4T tokens in all official 24 European languages.

1,493 Pulls 1 Tag Updated 1 year ago

promptnow/llama-3-typhoon-v1.5-8b-instruct-q4_k_m

Unofficial Llama-3-Typhoon-1.5-8B-instruct Q4_K_M Quantization (https://huggingface.co/scb10x/llama-3-typhoon-v1.5-8b-instruct)

551 Pulls 1 Tag Updated 1 year ago

Jatin19K/llamafactory_gemma-2-27b-instruct-q4_k_m

QLORA adaptor(q4) trained via Llamafactory from Huggingface's "google/gemma-2-27b-it", then merged(Q4_K_M) with Ollama's "gemma2:27b-instruct-fp16" using Ollama's Modelfile. Adaptor training data: HF's "JatinkInnovision/ShareGPT_Gemma2_it".

89 Pulls 1 Tag Updated 1 year ago