home-3b · Ollama

fixt/home-3b-v3

The "Home" model is a fine tuning of the StableLM-Zephyr-3B model. It achieves a score of 97.11% score for JSON function calling accuracy.

312K Pulls 7 Tags Updated 2 years ago

fixt/home-3b-v2

The "Home" model is a fine tuning of the Phi-2 model from Microsoft. The model is able to control devices in the user's smart home as well as perform basic question and answering.

7,153 Pulls 6 Tags Updated 2 years ago

fixt/home-3b-v1

The "Home" model is a fine tuning of the Phi-2 model from Microsoft. The model is able to control devices in the user's smart home as well as perform basic question and answering.

337 Pulls 3 Tags Updated 2 years ago

huihui_ai/kimi-k2

This is not the ablation version. Kimi-K2-Instruct is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters.

tools 1026b

12.2K Pulls 4 Tags Updated 1 year ago

huihui_ai/deepseek-v3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

7,196 Pulls 2 Tags Updated 1 year ago

huihui_ai/deepseek-v3-abliterated

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

671b

4,095 Pulls 5 Tags Updated 1 year ago

se0lx/stablehome-3b-rev9.q4_k_m

from acon96 / stablehome-multilingual-experimental

111 Pulls 1 Tag Updated 2 years ago

harishjan/llama_travel-conversation_trained_gguf

meta-llama/Llama-3.1-8B trained with soniawmeyer/travel-conversations-finetuning

3 Pulls 1 Tag Updated 1 year ago

AI-TAVS/Agents-A1-vision

Agents-A1: Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B Agent.

vision 4b 35b

67 Pulls 2 Tags Updated 1 month ago

Supa-AI/malaysian-llama-3.2-3b-instruct

Continue finetuning https://huggingface.co/meta-llama/Llama-3.2-3B on highly curated 1.5B tokens Malaysian instruction dataset.

281 Pulls 13 Tags Updated 1 year ago

cieloforge/Hiligaynon-llama-8b

PLTA's Fine-tune converted to Ollama model for ease of use. It's a Fine-tune of LlaMa 3.1 8B.

9 Pulls 1 Tag Updated 2 weeks ago

jikepjikep_16HEX/qwen3.6-35b-nightshift-heretic-uncensored-medic-a3b-moe-q4

😈 Uncensored Qwen3.6-35B (A3B MoE) Medic for Ollama, powered by #16HEX Matrix. Rust 1.98.0 Native Vision for medical imaging, radiology, emergency triage, laboratory diagnostics and clinical AI. 🚀

vision

392 Pulls 1 Tag Updated 2 weeks ago

nahiyananwar/mental-health-ai

Compassionate mental health support AI fine-tuned from Qwen 3 (14B) with 128K context.

116 Pulls 1 Tag Updated 3 months ago

aiasistentworld/Llama-3.1-8B-Instruct-STO-Master

The **Llama-3.1-8B-Instruct-STO-Master** is a high-performance fine-tune of Meta's Llama-3.1-8B-Instruct. This model represents the "Master Version" (Model E) of an extensive research project aimed at pushing the boundaries of 8B parameter architectures.

183 Pulls 1 Tag Updated 7 months ago

jbomdev/alterego

GGUF quantizations of https://huggingface.co/jbomdev/AlterEgo, a 373M-parameter decoder-only model built from the ground up: architecture, training, tokenizer, and inference all written from scratch. For the full story see the HF page

5 Pulls 3 Tags Updated 2 months ago

DavidDD/llamagurad38b

https://huggingface.co/meta-llama/Llama-Guard-3-8B

51 Pulls 1 Tag Updated 2 years ago

MHKetbi/OpenPipe_Deductive-Reasoning-Qwen-32B

Deductive Reasoning Qwen 32B is a reinforcement fine-tune of Qwen 2.5 32B Instruct to solve challenging deduction problems

tools

232 Pulls 7 Tags Updated 1 year ago