LFM2-350M

Home/Models/unsloth/LFM2-350M

unsloth/LFM2-350M

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-generation
root model: LiquidAI/LFM2-350M
provider: unsloth
license: other
language: en, ar, zh, fr, de, ja, ko, es
context: 32,768
library: transformers
vRAM (GB): —
size on disk: —
downloads: 542
likes: 4
created: —
last modified: 2025-07-14T12:38:37+00:00 (2025)
huggingface: https://huggingface.co/unsloth/LFM2-350M
tags: transformerssafetensorslfm2text-generationliquidunslothedgeconversationalenarzhfrdejakoesbase_model:LiquidAI/LFM2-350Mbase_model:finetune:LiquidAI/LFM2-350Mlicense:otherendpoints_compatibleregion:us

benchmark	category	score	conf	evidence
IFEval	instruction-following	65.12	high	`\| LFM2-350M \| 43.43 \| 27.46 \| 65.12 \| 16.41 \| 30.1 \| 29.52 \| 37.99 \|`
MMLU	knowledge	43.43	high	`\| LFM2-350M \| 43.43 \| 27.46 \| 65.12 \| 16.41 \| 30.1 \| 29.52 \| 37.99 \|`
GSM8K	math	30.1	high	`\| LFM2-350M \| 43.43 \| 27.46 \| 65.12 \| 16.41 \| 30.1 \| 29.52 \| 37.99 \|`
MGSM	math	29.52	high	`\| LFM2-350M \| 43.43 \| 27.46 \| 65.12 \| 16.41 \| 30.1 \| 29.52 \| 37.99 \|`
GPQA	reasoning	27.46	high	`\| LFM2-350M \| 43.43 \| 27.46 \| 65.12 \| 16.41 \| 30.1 \| 29.52 \| 37.99 \|`
IFBench	instruction-following	16.41	high	`\| LFM2-350M \| 43.43 \| 27.46 \| 65.12 \| 16.41 \| 30.1 \| 29.52 \| 37.99 \|`

none scraped.