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 • 7B • Updated • 351 • 50Note currently #1 with error rate of 0.353
deepseek-ai/deepseek-coder-1.3b-base
Text Generation • Updated • 17.4k • 111Note # previous #1 error rate 0.38
-
stabilityai/stable-code-3b
Text Generation • 3B • Updated • 8.64k • 660 -
bigcode/starcoder2-7b
Text Generation • 7B • Updated • 12.1k • 215 -
bigcode/starcoder2-3b
Text Generation • 3B • Updated • 123k • 219
Vipitis/santacoder-finetuned-Shadertoys-fine
Text Generation • 1B • Updated • 9Note has noteable difference between fp16 and fp32, will need to run bf16 likely contaminated
-
google/gemma-7b
Text Generation • 9B • Updated • 27.1k • • 3.35k -
google/codegemma-2b
Text Generation • 3B • Updated • 32.7k • • 100
Vipitis/santacoder-finetuned-Shadertoys
Text Generation • 1B • Updated • 17 • 2Note likely contaminated
Deci/DeciCoder-1b
Text Generation • 1B • Updated • 588 • 248Note 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 • 3B • Updated • 241k • • 1.19k
Salesforce/codegen2-1B_P
Text Generation • Updated • 942 • 41Note needs rerun with incomplete_generation tag
-
Vipitis/santacoder-finetuned-the-stack-glsl
Text Generation • 1B • Updated • 18 • 2 -
microsoft/phi-1_5
Text Generation • 1B • Updated • 57.2k • • 1.36k -
microsoft/phi-1
Text Generation • 1B • Updated • 10.2k • • 220
microsoft/phi-2
Text Generation • 3B • Updated • 458k • • 3.47kNote performs the worst with error rate of 0.79
ShaderMatch
🚀11code completion benchmark for GLSL shadercode
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
-
zai-org/codegeex2-6b
Updated • 225 • 258 -
deepseek-ai/deepseek-coder-5.7bmqa-base
Text Generation • Updated • 688 • 10 -
deepseek-ai/deepseek-coder-6.7b-base
Text Generation • 7B • Updated • 52.1k • 124 -
bigcode/gpt_bigcode-santacoder
Text Generation • 1B • Updated • 47.5k • 27 -
bigcode/starcoderbase
Text Generation • Updated • 14.6k • 418 -
google/codegemma-7b
Text Generation • 9B • Updated • 1.92k • 221 -
aiXcoder/aixcoder-7b-base
Text Generation • 7B • Updated • 514 • 55 -
Qwen/CodeQwen1.5-7B
Text Generation • 7B • Updated • 1.59k • 103 -
ibm-granite/granite-3b-code-base-2k
Text Generation • 3B • Updated • 13.1k • 38 -
mistralai/Codestral-22B-v0.1
22B • Updated • 13.4k • 1.33k -
deepseek-ai/DeepSeek-Coder-V2-Lite-Base
Text Generation • 16B • Updated • 3.83k • 111 -
Salesforce/codet5p-2b
Updated • 423 • 35 -
facebook/llm-compiler-7b
Text Generation • Updated • 140 -
meta-llama/Llama-3.1-8B
Text Generation • 8B • Updated • 1.27M • • 2.25k -
meta-llama/CodeLlama-7b-hf
Text Generation • Updated • 3.11k • 124 -
01-ai/Yi-Coder-9B
Text Generation • 9B • Updated • 8.02k • 45 -
Qwen/Qwen2.5-Coder-1.5B
Text Generation • 2B • Updated • 235k • • 92 -
Qwen/Qwen2.5-Coder-7B
Text Generation • 8B • Updated • 346k • • 147 -
infly/OpenCoder-1.5B-Base
Text Generation • 2B • Updated • 2.08k • 25 -
Qwen/Qwen2.5-Coder-0.5B
Text Generation • 0.5B • Updated • 24.3k • • 56