![](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 • 513 • 31Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 16.8k • 60Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 16.9k • 621bigcode/starcoder2-7b
Text Generation • Updated • 12.9k • 142bigcode/starcoder2-3b
Text Generation • Updated • 80.2k • 123
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 6 • 1Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 190k • 2.97kgoogle/codegemma-2b
Text Generation • Updated • 1.94k • 60
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 5 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 7.8k • 245Note 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 • 309k • 783
Salesforce/codegen2-1B_P
Text Generation • Updated • 3.26k • 36Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 2 • 3microsoft/phi-1_5
Text Generation • Updated • 84.9k • 1.3kmicrosoft/phi-1
Text Generation • Updated • 15.7k • 197
microsoft/phi-2
Text Generation • Updated • 423k • 3.2kNote performs the worst with error rate of 0.79
Running2🚀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 • 389 • 249deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 384 • 7deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 12.9k • 76codellama/CodeLlama-7b-hf
Text Generation • Updated • 63.2k • 307bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 25.5k • 24bigcode/starcoderbase
Text Generation • Updated • 1.39k • 387google/codegemma-7b
Text Generation • Updated • 4.9k • 136aiXcoder/aixcoder-7b-base
Text Generation • Updated • 60 • 44Qwen/CodeQwen1.5-7B
Text Generation • Updated • 3.46k • 79ibm-granite/granite-3b-code-base
Text Generation • Updated • 19k • 31mistralai/Codestral-22B-v0.1
Text Generation • Updated • 22.4k • 993deepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 3.66k • 29Salesforce/codet5p-2b
Text2Text Generation • Updated • 3.52k • 33facebook/llm-compiler-7b
Text Generation • Updated • 169 • 80