
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 • 2.08k • 43Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 95.6k • • 86Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 5.48k • 640bigcode/starcoder2-7b
Text Generation • Updated • 82.2k • 171bigcode/starcoder2-3b
Text Generation • Updated • 1.46M • • 167
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 38Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 38.7k • • 3.13kgoogle/codegemma-2b
Text Generation • Updated • 4.93k • • 78
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 42 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 3.56k • 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 • 274k • • 979
Salesforce/codegen2-1B_P
Text Generation • Updated • 1.18k • 39Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 225 • 2microsoft/phi-1_5
Text Generation • Updated • 115k • • 1.33kmicrosoft/phi-1
Text Generation • Updated • 6.66k • • 211
microsoft/phi-2
Text Generation • Updated • 415k • • 3.29kNote 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 • 287 • 253deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 698 • 8deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 28.5k • 101bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 51.2k • 25bigcode/starcoderbase
Text Generation • Updated • 1.77k • 401google/codegemma-7b
Text Generation • Updated • 3.2k • 179aiXcoder/aixcoder-7b-base
Text Generation • Updated • 105 • 52Qwen/CodeQwen1.5-7B
Text Generation • Updated • 2.01k • 96ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 5.8k • 38mistralai/Codestral-22B-v0.1
Text Generation • Updated • 12.9k • 1.23kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 183k • 75Salesforce/codet5p-2b
Text2Text Generation • Updated • 1.49k • 34facebook/llm-compiler-7b
Text Generation • Updated • 1.82k • 133meta-llama/Llama-3.1-8B
Text Generation • Updated • 1.33M • 1.48kmeta-llama/CodeLlama-7b-hf
Text Generation • Updated • 8.86k • 8701-ai/Yi-Coder-9B
Text Generation • Updated • 5.32k • 41Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 10.3k • • 51Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 57.6k • • 97infly/OpenCoder-1.5B-Base
Text Generation • Updated • 11.3k • 21Qwen/Qwen2.5-Coder-0.5B
Text Generation • Updated • 24.9k • • 26