
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 • 2.25k • 43Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 183k • • 87Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 6.62k • 643bigcode/starcoder2-7b
Text Generation • Updated • 74.2k • 173bigcode/starcoder2-3b
Text Generation • Updated • 1.31M • • 172
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 16Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 56.7k • • 3.14kgoogle/codegemma-2b
Text Generation • Updated • 3.93k • • 78
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 18 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 2.92k • 246Note 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 • 379k • • 986
Salesforce/codegen2-1B_P
Text Generation • Updated • 2.8k • • 39Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 42 • 2microsoft/phi-1_5
Text Generation • Updated • 103k • • 1.33kmicrosoft/phi-1
Text Generation • Updated • 9.13k • • 211
microsoft/phi-2
Text Generation • Updated • 288k • • 3.29kNote performs the worst with error rate of 0.79
8ShaderMatch
🚀code completion benchmark for GLSL shadercode
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 • 304 • 254deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 795 • 8deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 57.4k • 102bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 55.7k • • 25bigcode/starcoderbase
Text Generation • Updated • 2.89k • 403google/codegemma-7b
Text Generation • Updated • 3.76k • 179aiXcoder/aixcoder-7b-base
Text Generation • Updated • 73 • 53Qwen/CodeQwen1.5-7B
Text Generation • Updated • 2.44k • 97ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 2.09k • 37mistralai/Codestral-22B-v0.1
Text Generation • Updated • 9.54k • 1.24kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 134k • 76Salesforce/codet5p-2b
Text2Text Generation • Updated • 1.07k • 34facebook/llm-compiler-7b
Text Generation • Updated • 923 • 134meta-llama/Llama-3.1-8B
Text Generation • Updated • 986k • 1.53kmeta-llama/CodeLlama-7b-hf
Text Generation • Updated • 4.73k • 9401-ai/Yi-Coder-9B
Text Generation • Updated • 4.82k • 41Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 22k • • 52Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 78.2k • • 97infly/OpenCoder-1.5B-Base
Text Generation • Updated • 305 • 21Qwen/Qwen2.5-Coder-0.5B
Text Generation • Updated • 15.4k • • 26