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 • 2.7k • 37Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 42.6k • 64Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 9.51k • 634bigcode/starcoder2-7b
Text Generation • Updated • 68.3k • 160bigcode/starcoder2-3b
Text Generation • Updated • 197k • • 147
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 21Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 296k • • 3.05kgoogle/codegemma-2b
Text Generation • Updated • 5.84k • 72
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 51 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 1.64k • 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 • 437k • 912
Salesforce/codegen2-1B_P
Text Generation • Updated • 1.87k • 38Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 29 • 2microsoft/phi-1_5
Text Generation • Updated • 132k • 1.31kmicrosoft/phi-1
Text Generation • Updated • 9.21k • 207
microsoft/phi-2
Text Generation • Updated • 233k • 3.24kNote 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 • 204 • 251deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 899 • 7deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 42.4k • 80bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 27.5k • 25bigcode/starcoderbase
Text Generation • Updated • 846 • 394google/codegemma-7b
Text Generation • Updated • 4.13k • 165aiXcoder/aixcoder-7b-base
Text Generation • Updated • 132 • 52Qwen/CodeQwen1.5-7B
Text Generation • Updated • 2.3k • 92ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 35.2k • 35mistralai/Codestral-22B-v0.1
Text Generation • Updated • 9.8k • 1.15kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 8.18k • 59Salesforce/codet5p-2b
Text2Text Generation • Updated • 532 • 33facebook/llm-compiler-7b
Text Generation • Updated • 36.5k • 121meta-llama/Llama-3.1-8B
Text Generation • Updated • 1.06M • 1.06kmeta-llama/CodeLlama-7b-hf
Text Generation • Updated • 13.2k • 6901-ai/Yi-Coder-9B
Text Generation • Updated • 6.93k • 39Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 17k • 31Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 28.6k • 54infly/OpenCoder-1.5B-Base
Text Generation • Updated • 282 • 13