HF Model & Benchmark Matrix

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

Qwen2.5-0.5B

Qwen/Qwen2.5-0.5B

kind
original
quant
bf16 (16-bit)
family
qwen
modality
text-generation
root model
Qwen/Qwen2.5-0.5B
provider
Qwen
license
apache-2.0
language
en
context
32,768
library
transformers
vRAM (GB)
—
size on disk
—
downloads
2,573,601
likes
433
created
—
last modified
2024-09-25T12:32:36+00:00 (2024)
huggingface
https://huggingface.co/Qwen/Qwen2.5-0.5B
tags
transformerssafetensorsqwen2text-generationconversationalenarxiv:2407.10671license:apache-2.0eval-resultstext-generation-inferenceendpoints_compatibledeploy:azureregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (16)

titleauthorstatuscommentstype
Listed on OpenModelMapduola15open0disc
TemporalMesh Transformer: 29.4 PPL at 48% compute — dynamic graph attention + adaptive exit gates (open-source, 226 tests)vigneshwar234open0disc
Add EvalEval community eval resultsEvalEvalBotopen0disc
model compatability to implement watermarksHadiya1open0disc
Update README.mdPerido353522open0disc
myrequestssinchanonlydraft0disc
daddyshome999tomydraft0disc
Add link to Neuron-optimized versionbadaouiopen0disc
add link to new model versiondavanstrienopen0disc
Model input shape18marie05open0disc
System Prompt Ignoredpublicmutinyopen0disc
any tfite versionNimurAIopen0disc
FIM-Tokens not marked specialruedisteopen0disc
TypeError: Qwen2Model.forward() got an unexpected keyword argument 'labels'Lijensopen0disc
VRAM Requirementsahmaddanyalopen0disc
Update metadata: Add library_name to Transformersxianbaomerged0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.