LFM2-1.2B

Home/Models/unsloth/LFM2-1.2B

unsloth/LFM2-1.2B

kind: original
quant: bf16 (16-bit)
family: misc
modality: text-generation
root model: LiquidAI/LFM2-1.2B
provider: unsloth
license: other
language: en, ar, zh, fr, de, ja, ko, es
context: 32,768
library: transformers
vRAM (GB): —
size on disk: —
downloads: 98
likes: 12
created: —
last modified: 2025-07-14T12:34:58+00:00 (2025)
huggingface: https://huggingface.co/unsloth/LFM2-1.2B
tags: transformerssafetensorslfm2text-generationliquidunslothedgeconversationalenarzhfrdejakoesbase_model:LiquidAI/LFM2-1.2Bbase_model:finetune:LiquidAI/LFM2-1.2Blicense:otherendpoints_compatibleregion:us

benchmark	category	score	conf	evidence
IFEval	instruction-following	74.89	high	`\| LFM2-1.2B \| 55.23 \| 31.47 \| 74.89 \| 20.7 \| 58.3 \| 55.04 \| 46.73 \|`
GSM8K	math	58.3	high	`\| LFM2-1.2B \| 55.23 \| 31.47 \| 74.89 \| 20.7 \| 58.3 \| 55.04 \| 46.73 \|`
MMLU	knowledge	55.23	high	`\| LFM2-1.2B \| 55.23 \| 31.47 \| 74.89 \| 20.7 \| 58.3 \| 55.04 \| 46.73 \|`
MGSM	math	55.04	high	`\| LFM2-1.2B \| 55.23 \| 31.47 \| 74.89 \| 20.7 \| 58.3 \| 55.04 \| 46.73 \|`
GPQA	reasoning	31.47	high	`\| LFM2-1.2B \| 55.23 \| 31.47 \| 74.89 \| 20.7 \| 58.3 \| 55.04 \| 46.73 \|`
IFBench	instruction-following	20.7	high	`\| LFM2-1.2B \| 55.23 \| 31.47 \| 74.89 \| 20.7 \| 58.3 \| 55.04 \| 46.73 \|`

none scraped.