ministral 8b · Ollama

vrozax1337/ministral-3-8b-mlx

70 Pulls 1 Tag Updated 3 weeks ago

coreworxlab/caal-ministral

Fine-tuned Ministral-3 8B for tool-calling in CAAL, an open-source voice assistant by CoreWorxLab.

tools

527 Pulls 3 Tags Updated 6 months ago

peacedude/ministral-3-8b-techcwbldr

tools thinking

15 Pulls 1 Tag Updated 3 months ago

nchapman/ministral-8b-instruct-2410

Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks.

tools 8b

1,874 Pulls 2 Tags Updated 1 year ago

cas/ministral-8b-instruct-2410_q4km

early testing quants of Mistral/Ministral-8B-Instruct-2410. for research purposes as per https://mistral.ai/licenses/MRL-0.1.md

tools

1,619 Pulls 1 Tag Updated 1 year ago

Supa-AI/ministral-8b-instruct-2410

Quantized versions of the new ministral 8B! This is purely for research purposes and not for commercial distribution

647 Pulls 13 Tags Updated 1 year ago

redule26/ministral-8b

The Ministral-8B-Instruct-2410 Language Model is an instruct fine-tuned model significantly outperforming existing models of similar size, released under the Mistral Research License.

563 Pulls 3 Tags Updated 1 year ago

artcx001/Ministral-8B-Instruct-2410

Working Ministral models

557 Pulls 10 Tags Updated 1 year ago

saki007ster/fine-tuned_Ministral-8B

tools

20 Pulls 1 Tag Updated 1 year ago

doomgrave/ministral-3

ministral-3:8b quantized to Q4_K_S for lower vram devices.

vision tools 8b

511 Pulls 2 Tags Updated 8 months ago

pstdio/microcoder

Attempt at using the ministral-3:8b reasoning version for coding tasks.

vision tools thinking 3b 8b

304 Pulls 2 Tags Updated 7 months ago

Maoyue/mistral-nemo-minitron-8b-instruct

Mistral-NeMo-Minitron-8B-Instruct by nvidia, GGUF file from MaoyueOUO/mistral-nemo-minitron-8b-instruct-GGUF on hf.

tools

263 Pulls 1 Tag Updated 1 year ago

schroneko/mistral-nemo-minitron-8b-instruct

Mistral-NeMo-Minitron-8B-Instruct is a model for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling.

1,259 Pulls 14 Tags Updated 1 year ago

kuro/mistral-nemo-minitron-8b-base-q8_0-gguf

Mistral-NeMo-Minitron-8B-Base:Q8_0

tools

394 Pulls 1 Tag Updated 2 years ago

mseri/mistral-nemo-minitron

Mistral NeMo Minitron 8B Instruct with correct stop params

tools

140 Pulls 1 Tag Updated 1 year ago

jessicalw34/TORUS

TORUS is a SnapKitty finance-focused language model fine-tuned for financial research and structured analysis. (Mistral 8B — orchestrator) temperature 0.1 top_k 30 top_p 0.9 num_ctx 8192,

1 Pull 1 Tag Updated yesterday

whiskeyjax/medical-nemo-q8-lora

A Mistral Nemo model finetuned using 8bit QLoRA using a medical questions database

tools

79 Pulls 1 Tag Updated 1 year ago