models to evaluate
collecting models I want to evaluate on shadereval-task2: https://github.com/bigcode-project/bigcode-evaluation-harness/pull/173 at fp16!!
Text Generation • Updated • 3.79k • 37Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 20.6k • 64Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 7.98k • 633bigcode/starcoder2-7b
Text Generation • Updated • 27.5k • 158bigcode/starcoder2-3b
Text Generation • Updated • 141k • 143
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 30 • 1Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 270k • 3.05kgoogle/codegemma-2b
Text Generation • Updated • 5.49k • 69
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 45 • 3Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 5.59k • 247Note current result is not fully correct, need to rerun model - however I don't know a transformers version that runs without errors
google/gemma-2b
Text Generation • Updated • 519k • 905
Salesforce/codegen2-1B_P
Text Generation • Updated • 4.45k • 38Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 37 • 3microsoft/phi-1_5
Text Generation • Updated • 134k • 1.31kmicrosoft/phi-1
Text Generation • Updated • 8.67k • 203
microsoft/phi-2
Text Generation • Updated • 255k • 3.24kNote performs the worst with error rate of 0.79
Running7🚀ShaderMatch
Note this space holds the evaluation metric that is used. It also has a usually up to date leaderboard. check for updates: https://huggingface.co/spaces/Vipitis/shadermatch/blob/main/result_preview.png
THUDM/codegeex2-6b
Updated • 150 • 251deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 645 • 7deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 21.6k • 80bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 28.7k • 25bigcode/starcoderbase
Text Generation • Updated • 755 • 394google/codegemma-7b
Text Generation • Updated • 6.94k • 161aiXcoder/aixcoder-7b-base
Text Generation • Updated • 57 • 52Qwen/CodeQwen1.5-7B
Text Generation • Updated • 6.99k • 90ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 58.1k • 35mistralai/Codestral-22B-v0.1
Text Generation • Updated • 10.9k • 1.13kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 6.72k • 57Salesforce/codet5p-2b
Text2Text Generation • Updated • 426 • 33facebook/llm-compiler-7b
Text Generation • Updated • 2.16k • 120meta-llama/Llama-3.1-8B
Text Generation • Updated • 918k • 978meta-llama/CodeLlama-7b-hf
Text Generation • Updated • 9.7k • 6701-ai/Yi-Coder-9B
Text Generation • Updated • 7.92k • 39Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 7.27k • 26Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 22.9k • 33