Seed-Coder-8B-Instruct-GGUF

Home/Models/unsloth/Seed-Coder-8B-Instruct-GGUF

unsloth/Seed-Coder-8B-Instruct-GGUF

kind: gguf
quant: gguf (16-bit)
family: misc
modality: text-generation
root model: ByteDance-Seed/Seed-Coder-8B-Instruct
provider: unsloth
license: mit
language: —
context: 32,768
library: transformers
vRAM (GB): —
size on disk: —
downloads: 1,729
likes: 12
created: —
last modified: 2025-05-18T13:42:55+00:00 (2025)
huggingface: https://huggingface.co/unsloth/Seed-Coder-8B-Instruct-GGUF
tags: transformersggufllamatext-generationunslothbase_model:ByteDance-Seed/Seed-Coder-8B-Instructbase_model:quantized:ByteDance-Seed/Seed-Coder-8B-Instructlicense:mitendpoints_compatibleregion:usconversational

benchmark	category	score	conf	evidence
MBPP	coding	85.2	high	`\| Seed-Coder-8B-Instruct \| 84.8 \| 85.2 \| 36.2 \| 53.3 \| 26.4 \| 24.7 \|`
HumanEval	coding	84.8	high	`\| Seed-Coder-8B-Instruct \| 84.8 \| 85.2 \| 36.2 \| 53.3 \| 26.4 \| 24.7 \|`
BigCodeBench	coding	53.3	high	`\| Seed-Coder-8B-Instruct \| 84.8 \| 85.2 \| 36.2 \| 53.3 \| 26.4 \| 24.7 \|`
LiveCodeBench	coding	24.7	high	`\| Seed-Coder-8B-Instruct \| 84.8 \| 85.2 \| 36.2 \| 53.3 \| 26.4 \| 24.7 \|`

none scraped.