![](https://cdn-avatars.huggingface.co/v1/production/uploads/6538815d1bdb3c40db94fbfa/xMBly9PUMphrFVMxLX4kq.png)
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 • 1.09k • 43Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 57.3k • 78Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 6.1k • 638bigcode/starcoder2-7b
Text Generation • Updated • 14.1k • 168bigcode/starcoder2-3b
Text Generation • Updated • 636k • 161
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 17Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 69.8k • 3.11kgoogle/codegemma-2b
Text Generation • Updated • 8.81k • 78
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 25 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 2.45k • 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 • 250k • • 961
Salesforce/codegen2-1B_P
Text Generation • Updated • 820 • 38Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 41 • 2microsoft/phi-1_5
Text Generation • Updated • 118k • 1.32kmicrosoft/phi-1
Text Generation • Updated • 5.61k • 210
microsoft/phi-2
Text Generation • Updated • 312k • 3.27kNote performs the worst with error rate of 0.79
8ShaderMatch
🚀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 • 146 • 253deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 935 • 8deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 43.1k • 96bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 44k • 25bigcode/starcoderbase
Text Generation • Updated • 1.41k • 398google/codegemma-7b
Text Generation • Updated • 3.83k • 176aiXcoder/aixcoder-7b-base
Text Generation • Updated • 66 • 52Qwen/CodeQwen1.5-7B
Text Generation • Updated • 3.9k • 94ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 7.28k • 36mistralai/Codestral-22B-v0.1
Text Generation • Updated • 730k • 1.21kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 13.4k • 73Salesforce/codet5p-2b
Text2Text Generation • Updated • 508 • 33facebook/llm-compiler-7b
Text Generation • Updated • 775 • 127meta-llama/Llama-3.1-8B
Text Generation • Updated • 1.13M • 1.37kmeta-llama/CodeLlama-7b-hf
Text Generation • Updated • 28.1k • 7901-ai/Yi-Coder-9B
Text Generation • Updated • 7.64k • 39Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 14.8k • 44Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 36.3k • 89infly/OpenCoder-1.5B-Base
Text Generation • Updated • 5.65k • 20Qwen/Qwen2.5-Coder-0.5B
Text Generation • Updated • 13.5k • 19