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 • 466 • 37Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 50.4k • 66Note # previous #1 error rate 0.38
stabilityai/stable-code-3b
Text Generation • Updated • 5.88k • 637bigcode/starcoder2-7b
Text Generation • Updated • 9.88k • 164bigcode/starcoder2-3b
Text Generation • Updated • 303k • 153
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • Updated • 18Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
google/gemma-7b
Text Generation • Updated • 37k • 3.09kgoogle/codegemma-2b
Text Generation • Updated • 1.87k • 74
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • Updated • 21 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • Updated • 1.37k • 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 • 306k • 934
Salesforce/codegen2-1B_P
Text Generation • Updated • 569 • 38Note needs rerun with incomplete_generation tag
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • Updated • 16 • 2microsoft/phi-1_5
Text Generation • Updated • 121k • 1.32kmicrosoft/phi-1
Text Generation • Updated • 3.61k • 207
microsoft/phi-2
Text Generation • Updated • 158k • 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 • 398 • 253deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 342 • 7deepseek-ai/deepseek-coder-6.7b-base
Text Generation • Updated • 17.6k • 86bigcode/gpt_bigcode-santacoder
Text Generation • Updated • 25.9k • 25bigcode/starcoderbase
Text Generation • Updated • 3.27k • 395google/codegemma-7b
Text Generation • Updated • 2.8k • 171aiXcoder/aixcoder-7b-base
Text Generation • Updated • 63 • 52Qwen/CodeQwen1.5-7B
Text Generation • Updated • 10.6k • 92ibm-granite/granite-3b-code-base-2k
Text Generation • Updated • 5.59k • 36mistralai/Codestral-22B-v0.1
Text Generation • Updated • 3.76M • 1.17kdeepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • Updated • 10.2k • 66Salesforce/codet5p-2b
Text2Text Generation • Updated • 396 • 33facebook/llm-compiler-7b
Text Generation • Updated • 1.04k • 127meta-llama/Llama-3.1-8B
Text Generation • Updated • 588k • 1.25kmeta-llama/CodeLlama-7b-hf
Text Generation • Updated • 4.17k • 7501-ai/Yi-Coder-9B
Text Generation • Updated • 6.05k • 39Qwen/Qwen2.5-Coder-1.5B
Text Generation • Updated • 17.3k • 35Qwen/Qwen2.5-Coder-7B
Text Generation • Updated • 19.2k • 84infly/OpenCoder-1.5B-Base
Text Generation • Updated • 556 • 18Qwen/Qwen2.5-Coder-0.5B
Text Generation • Updated • 11.4k • 16