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 • 928 • 37Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 40.3k • 65Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 7.88k • 636bigcode/starcoder2-7b
Text Generation • Updated • 18k • 163bigcode/starcoder2-3b
Text Generation • Updated • 319k • 153
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 27Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 52.7k • 3.08kgoogle/codegemma-2b
Text Generation • Updated • 1.79k • 74
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 28 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 1.69k • 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 • 418k • 925
Salesforce/codegen2-1B_P
Text Generation • Updated • 657 • 38Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 23 • 2microsoft/phi-1_5
Text Generation • Updated • 136k • 1.32kmicrosoft/phi-1
Text Generation • Updated • 6.73k • 207
microsoft/phi-2
Text Generation • Updated • 183k • 3.26kNote 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 • 357 • 253deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 603 • 7deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 41.9k • 85bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 41.6k • 25bigcode/starcoderbase
Text Generation • Updated • 1.12k • 395google/codegemma-7b
Text Generation • Updated • 2.88k • 170aiXcoder/aixcoder-7b-base
Text Generation • Updated • 86 • 52Qwen/CodeQwen1.5-7B
Text Generation • Updated • 10.6k • 91ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 3.86k • 36mistralai/Codestral-22B-v0.1
Text Generation • Updated • 3.11M • 1.17kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 10.9k • 62Salesforce/codet5p-2b
Text2Text Generation • Updated • 309 • 33facebook/llm-compiler-7b
Text Generation • Updated • 3.07k • 126meta-llama/Llama-3.1-8B
Text Generation • Updated • 739k • 1.23kmeta-llama/CodeLlama-7b-hf
Text Generation • Updated • 3.4k • 7501-ai/Yi-Coder-9B
Text Generation • Updated • 6.55k • 39Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 11.7k • 35Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 30.2k • 83infly/OpenCoder-1.5B-Base
Text Generation • Updated • 909 • 17Qwen/Qwen2.5-Coder-0.5B
Text Generation • Updated • 11.8k • 16