| { |
| "seen_models": [ |
| "01-ai/Yi-1.5-6B-Chat", |
| "01-ai/Yi-1.5-9B-Chat", |
| "EleutherAI/gpt-j-6b", |
| "EleutherAI/gpt-neox-20b", |
| "HuggingFaceTB/SmolLM2-1.7B-Instruct", |
| "Qwen/Qwen2.5-0.5B-Instruct", |
| "Qwen/Qwen2.5-1.5B-Instruct", |
| "Qwen/Qwen2.5-3B-Instruct", |
| "Qwen/Qwen2.5-7B-Instruct", |
| "Qwen/Qwen3-14B", |
| "allenai/OLMo-2-1124-13B-Instruct", |
| "allenai/OLMo-2-1124-7B-Instruct", |
| "berkeley-nest/Starling-LM-7B-alpha", |
| "deepseek-ai/deepseek-llm-7b-chat", |
| "google/gemma-2-2b-it", |
| "google/gemma-3-12b-it", |
| "google/gemma-3-27b-it", |
| "ibm-granite/granite-3.0-2b-instruct", |
| "ibm-granite/granite-3.0-8b-instruct", |
| "internlm/internlm2-7b", |
| "internlm/internlm2_5-20b-chat", |
| "meta-llama/Llama-2-13b-chat-hf", |
| "meta-llama/Llama-3.1-8B-Instruct", |
| "meta-llama/Llama-3.2-3B-Instruct", |
| "microsoft/Phi-3-medium-4k-instruct", |
| "microsoft/Phi-3-mini-4k-instruct", |
| "microsoft/phi-2", |
| "microsoft/phi-4", |
| "mistralai/Mistral-7B-Instruct-v0.3", |
| "mistralai/Mistral-Small-24B-Instruct-2501", |
| "mistralai/Mistral-Small-Instruct-2409", |
| "mlabonne/AlphaMonarch-7B", |
| "mlabonne/NeuralBeagle14-7B", |
| "nvidia/AceMath-1.5B-Instruct", |
| "nvidia/AceMath-7B-Instruct", |
| "nvidia/Llama-3.1-Minitron-4B-Width-Base", |
| "nvidia/Mistral-NeMo-Minitron-8B-Instruct", |
| "nvidia/Nemotron-Mini-4B-Instruct", |
| "openai-community/gpt2", |
| "tiiuae/Falcon3-3B-Instruct", |
| "upstage/SOLAR-10.7B-Instruct-v1.0", |
| "upstage/solar-pro-preview-instruct" |
| ], |
| "seen_gpus": [ |
| "A100 SXM4 40 GB", |
| "A30 PCIe", |
| "H100 NVL 94 GB", |
| "H200 NVL", |
| "L4", |
| "L40S", |
| "Tesla T4", |
| "Tesla V100 SXM2 32 GB" |
| ], |
| "power_features": [ |
| "scenario", |
| "log_total_b_params", |
| "model_type", |
| "num_key_value_heads", |
| "num_layers", |
| "memory_bandwidth_gb_s", |
| "boost_percentage", |
| "transistor_count_m", |
| "base_clock_mhz", |
| "release_year", |
| "bandwidth_latency" |
| ], |
| "itl_features": [ |
| "scenario", |
| "model_type", |
| "total_b_params", |
| "hidden_size", |
| "num_attention_heads", |
| "num_key_value_heads", |
| "num_layers", |
| "memory_bandwidth_gb_s", |
| "memory_size_gb", |
| "memory_type", |
| "tflops_16b", |
| "release_year", |
| "bandwidth_latency", |
| "compute_latency_s" |
| ], |
| "tier_accuracy_mdape": { |
| "power": { |
| "green": { |
| "offline": 1.8, |
| "server": 5.6 |
| }, |
| "yellow": { |
| "offline": 2.1, |
| "server": 6.6 |
| }, |
| "orange": { |
| "offline": 3.6, |
| "server": 15.1 |
| }, |
| "red": { |
| "offline": 4.0, |
| "server": 16.9 |
| } |
| }, |
| "itl": { |
| "green": { |
| "offline": 12.8, |
| "server": 4.9 |
| }, |
| "yellow": { |
| "offline": 15.6, |
| "server": 5.6 |
| }, |
| "orange": { |
| "offline": 24.9, |
| "server": 8.5 |
| }, |
| "red": { |
| "offline": 36.2, |
| "server": 8.6 |
| } |
| } |
| }, |
| "log_transformed_targets": [ |
| "itl" |
| ], |
| "n_training_runs": { |
| "power": 4213, |
| "itl": 4163 |
| }, |
| "gpu_tdp": { |
| "A100 SXM4 40 GB": 400.0, |
| "A30 PCIe": 165.0, |
| "H100 NVL 94 GB": 400.0, |
| "H200 NVL": 700.0, |
| "L4": 72.0, |
| "L40S": 350.0, |
| "Tesla T4": 70.0, |
| "Tesla V100 SXM2 32 GB": 300.0 |
| } |
| } |
