Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
BobbieBieee
/
Osprey-Speculative-Decoding
Like
0
Safetensors
speculative-decoding
eagle3
draft-model
sglang
arxiv:
2609.09338
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Osprey-Speculative-Decoding
/
data
3.87 GB
Ctrl+K
Ctrl+K
1 contributor
History:
10 commits
BobbieBieee
Add math_train_65k_qwen3_8B_4096.jsonl
888602f
verified
about 1 month ago
chat_eval_512_qwen3_8B_4096.jsonl
Safe
2.7 MB
Add the five-domain evaluation splits (512 prompts each)
about 1 month ago
chat_train_65k_qwen3_8B_4096.jsonl
Safe
350 MB
xet
Add chat_train_65k_qwen3_8B_4096.jsonl
about 1 month ago
code_eval_512_minimax_m25_4096.jsonl
Safe
8.11 MB
Add MiniMax-M2.5 evaluation split (code_eval_512_minimax_m25_4096.jsonl)
about 1 month ago
code_eval_512_qwen3_8B_4096.jsonl
Safe
7.04 MB
Add the five-domain evaluation splits (512 prompts each)
about 1 month ago
code_train_65k_qwen3_8B_4096.jsonl
Safe
917 MB
xet
Add code_train_65k_qwen3_8B_4096.jsonl
about 1 month ago
code_train_70k_minimax_m25_4096.jsonl
Suspicious
1.12 GB
xet
Add MiniMax-M2.5 training split (code_train_70k_minimax_m25_4096.jsonl)
about 1 month ago
commonsense_eval_512_qwen3_8B_4096.jsonl
Safe
2.55 MB
Add the five-domain evaluation splits (512 prompts each)
about 1 month ago
commonsense_train_65k_qwen3_8B_4096.jsonl
Safe
327 MB
xet
Add commonsense_train_65k_qwen3_8B_4096.jsonl
about 1 month ago
finance_eval_512_qwen3_8B_4096.jsonl
Safe
3.11 MB
Add the five-domain evaluation splits (512 prompts each)
about 1 month ago
finance_train_65k_qwen3_8B_4096.jsonl
Safe
392 MB
xet
Add finance_train_65k_qwen3_8B_4096.jsonl
about 1 month ago
math_eval_512_qwen3_8B_4096.jsonl
Safe
3.49 MB
Add the five-domain evaluation splits (512 prompts each)
about 1 month ago
math_train_65k_qwen3_8B_4096.jsonl
Safe
453 MB
xet
Add math_train_65k_qwen3_8B_4096.jsonl
about 1 month ago
perfectblend_eval_512_llama33_70b.jsonl
Safe
1.56 MB
Add Llama-3.3-70B-Instruct evaluation split (512)
about 1 month ago
perfectblend_train_100k_llama33_70b.jsonl
Suspicious
287 MB
xet
Add Llama-3.3-70B-Instruct adaptation split (100k, PerfectBlend regenerated)
about 1 month ago
