HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Llama-3.2-1B

meta-llama/Llama-3.2-1B

kind
original
quant
bf16 (16-bit)
family
llama
modality
text-generation
root model
meta-llama/Llama-3.2-1B
provider
meta-llama
license
llama3.2
language
en, de, fr, it, pt, hi, es, th
context
—
library
transformers
vRAM (GB)
2,529
size on disk
—
downloads
1,796,222
likes
2,507
created
—
last modified
2024-10-24T15:08:03+00:00 (2024)
huggingface
https://huggingface.co/meta-llama/Llama-3.2-1B
tags
transformerssafetensorsllamatext-generationfacebookmetapytorchllama-3endefritpthiestharxiv:2204.05149arxiv:2405.16406license:llama3.2eval-resultstext-generation-inferenceendpoints_compatibleregion:usdeploy:sagemaker

Benchmark scores (1)

benchmarkcategoryscorecontextconfevidence
MATHmath44.4Mathmedium| Math | | GSM8K (CoT) | 8 | em\_maj1@1 | 44.4 | 33.1 | 40.6 | 46.5 | 77.7 | 72.9 | 75.7 | 77.9 | 84.5 |

Discussions (12)

titleauthorstatuscommentstype
Request to reset access request for Llama-3.2-1BKira04open0disc
Request to reset and reconsider my rejected Llama 3.2 access applicationsmallphanclosed0disc
Request: DOIpradeeppkopen0disc
Appeal for Reconsideration of Access Request to meta-llama/Llama-3.2-1BPrestyanopen0disc
Request: DOIMichominaopen0disc
Can I please get the request approved?paogegeopen0disc
AccessAsishDdraft0disc
Appeal for Rejected Access Request - meta-llama/Llama-3.2-1BMikeYuanopen0disc
Access RequestJenjamcopen0disc
TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecturevigneshwar234open0disc
Add EvalEval community eval resultsEvalEvalBotopen0disc
Request: DOIoptiviseappopen0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.