What are the hardware requirements for TinyMistral V2 Test1?

TinyMistral V2 Test1 requires approximately 1 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TinyMistral V2 Test1 and how large is it?

TinyMistral V2 Test1 is developed by Dans-DiscountModels, a model with 248m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does TinyMistral V2 Test1 perform on standard benchmarks?

TinyMistral V2 Test1 has the following published scores: MMLU 23.36. Compare against reference models on this page or on the LLM Explorer leaderboards.

TinyMistral V2 Test1 by Dans-DiscountModels — VRAM 1GB, 32K context

Name: TinyMistral V2 Test1
Author: Dans-DiscountModels

TinyMistral V2 Test1 is an open-source language model by Dans-DiscountModels. Features: 248m LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.15, Arc: 21.5, HellaSwag: 26.8, MMLU: 23.4.

Autotrain compatible Base model:finetune:locutusque... Base model:locutusque/tinymist... Dataset:epfl-llm/guidelines Dataset:jeankaddour/minipile En Endpoints compatible Generated from trainer Mistral Pytorch Region:us

Model Card on HF 🤗: https://huggingface.co/Dans-DiscountModels/TinyMistral-v2-Test1

TinyMistral V2 Test1 Parameters and Internals

Model Type

MistralForCausalLM

Supported Languages

en (unknown)

Training Details

Data Sources:

JeanKaddour/minipile, epfl-llm/guidelines

Context Length:

2048

LLM Name	TinyMistral V2 Test1
Repository 🤗	https://huggingface.co/Dans-DiscountModels/TinyMistral-v2-Test1
Base Model(s)	TinyMistral 248M V2 Locutusque/TinyMistral-248M-v2
Model Size	248m
Required VRAM	1 GB
Updated	2024-12-02
Maintainer	Dans-DiscountModels
Model Type	mistral
Model Files	1.0 GB
Supported Languages	en
Model Architecture	MistralForCausalLM
License	apache-2.0
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	32005
Torch Data Type	float32

Rank the TinyMistral V2 Test1 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to TinyMistral V2 Test1

Best Alternatives	Context / RAM	Downloads	Likes
TinyMistral 248M V2.5	32K / 1 GB	226	27
TinyMistral 248M V2	32K / 1 GB	1096	17
TinyMistral 248M V2.5 Instruct	32K / 1 GB	2	11
...al V2.5 MiniPile Guidelines E1	32K / 0.6 GB	13	2
...adrin TinyMistral248M Instruct	32K / 0.5 GB	108	7
TinyMistral 248M Instruct	32K / 1 GB	69	12
TinyMistral 248M 8bits	32K / 0.3 GB	21	1
Tinymistv1	32K / 0.5 GB	17	0
TinyMistral Haiku	32K / 1 GB	10	0
TinyMistral 248M V3	32K / 0.5 GB	197	8

Note: green Score (e.g. "73.2") means that the model is better than Dans-DiscountModels/TinyMistral-v2-Test1.