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 • 1.67k • 37Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 46.6k • 65Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 6.86k • 636bigcode/starcoder2-7b
Text Generation • Updated • 58.8k • 161bigcode/starcoder2-3b
Text Generation • Updated • 284k • 152
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 29Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 189k • 3.06kgoogle/codegemma-2b
Text Generation • Updated • 4.58k • 73
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 31 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 1.67k • 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 • 397k • 917
Salesforce/codegen2-1B_P
Text Generation • Updated • 590 • 38Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 26 • 2microsoft/phi-1_5
Text Generation • Updated • 125k • 1.32kmicrosoft/phi-1
Text Generation • Updated • 10.1k • 207
microsoft/phi-2
Text Generation • Updated • 203k • 3.25kNote performs the worst with error rate of 0.79
Running8🚀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 • 259 • 252deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 1.1k • 7deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 102k • 81bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 37.3k • 25bigcode/starcoderbase
Text Generation • Updated • 852 • 394google/codegemma-7b
Text Generation • Updated • 6.29k • 167aiXcoder/aixcoder-7b-base
Text Generation • Updated • 134 • 52Qwen/CodeQwen1.5-7B
Text Generation • Updated • 2.51k • 91ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 13.4k • 36mistralai/Codestral-22B-v0.1
Text Generation • Updated • 12.6k • 1.15kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 7.41k • 59Salesforce/codet5p-2b
Text2Text Generation • Updated • 404 • 33facebook/llm-compiler-7b
Text Generation • Updated • 35.7k • 122meta-llama/Llama-3.1-8B
Text Generation • Updated • 970k • 1.12kmeta-llama/CodeLlama-7b-hf
Text Generation • Updated • 11.3k • 7201-ai/Yi-Coder-9B
Text Generation • Updated • 7.04k • 39Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 17.1k • 35Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 34.5k • 73infly/OpenCoder-1.5B-Base
Text Generation • Updated • 2.04k • 17Qwen/Qwen2.5-Coder-0.5B
Text Generation • Updated • 11.4k • 11