Text Generation
Transformers
Safetensors
mistral
nvfp4
conversational
text-generation-inference
8-bit precision
compressed-tensors
Instructions to use DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8") model = AutoModelForCausalLM.from_pretrained("DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8
- SGLang
How to use DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8 with Docker Model Runner:
docker model run hf.co/DataSnake/Mistral-Nemo-Instruct-2407-NVFP4-FP8
Upload benchmarks.json
Browse files- benchmarks.json +370 -0
benchmarks.json
ADDED
|
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"Mistral-Nemo-Instruct-2407-NVFP4": {
|
| 3 |
+
"coqa": {
|
| 4 |
+
"alias": "coqa",
|
| 5 |
+
"em,none": 0.5391666666666667,
|
| 6 |
+
"em_stderr,none": 0.019942406218865946,
|
| 7 |
+
"f1,none": 0.7182411035342305,
|
| 8 |
+
"f1_stderr,none": 0.015116252267763605
|
| 9 |
+
},
|
| 10 |
+
"hellaswag": {
|
| 11 |
+
"alias": "hellaswag",
|
| 12 |
+
"acc,none": 0.6186018721370244,
|
| 13 |
+
"acc_stderr,none": 0.004847372670134442,
|
| 14 |
+
"acc_norm,none": 0.8084047002589125,
|
| 15 |
+
"acc_norm_stderr,none": 0.003927519561403822
|
| 16 |
+
},
|
| 17 |
+
"ifeval": {
|
| 18 |
+
"alias": "ifeval",
|
| 19 |
+
"prompt_level_strict_acc,none": 0.3807763401109057,
|
| 20 |
+
"prompt_level_strict_acc_stderr,none": 0.020895937888190826,
|
| 21 |
+
"inst_level_strict_acc,none": 0.4712230215827338,
|
| 22 |
+
"inst_level_strict_acc_stderr,none": "N/A",
|
| 23 |
+
"prompt_level_loose_acc,none": 0.4602587800369686,
|
| 24 |
+
"prompt_level_loose_acc_stderr,none": 0.021448501434135032,
|
| 25 |
+
"inst_level_loose_acc,none": 0.5455635491606715,
|
| 26 |
+
"inst_level_loose_acc_stderr,none": "N/A"
|
| 27 |
+
},
|
| 28 |
+
"lambada_openai": {
|
| 29 |
+
"alias": "lambada_openai",
|
| 30 |
+
"perplexity,none": 3.0228658176330048,
|
| 31 |
+
"perplexity_stderr,none": 0.05627099222260382,
|
| 32 |
+
"acc,none": 0.7583931690277508,
|
| 33 |
+
"acc_stderr,none": 0.0059636738430670555
|
| 34 |
+
},
|
| 35 |
+
"lambada_openai_cloze_yaml": {
|
| 36 |
+
"alias": "lambada_openai_cloze_yaml",
|
| 37 |
+
"perplexity,none": 29.84274462902617,
|
| 38 |
+
"perplexity_stderr,none": 0.7625202924355495,
|
| 39 |
+
"acc,none": 0.3122452940034931,
|
| 40 |
+
"acc_stderr,none": 0.0064561975253284295
|
| 41 |
+
},
|
| 42 |
+
"lambada_standard": {
|
| 43 |
+
"alias": "lambada_standard",
|
| 44 |
+
"perplexity,none": 3.640092189793144,
|
| 45 |
+
"perplexity_stderr,none": 0.07656519320424794,
|
| 46 |
+
"acc,none": 0.688530952843004,
|
| 47 |
+
"acc_stderr,none": 0.006451805320261074
|
| 48 |
+
},
|
| 49 |
+
"lambada_standard_cloze_yaml": {
|
| 50 |
+
"alias": "lambada_standard_cloze_yaml",
|
| 51 |
+
"perplexity,none": 44.843956670053444,
|
| 52 |
+
"perplexity_stderr,none": 1.1468558717049042,
|
| 53 |
+
"acc,none": 0.22588783233068116,
|
| 54 |
+
"acc_stderr,none": 0.005825865294666935
|
| 55 |
+
},
|
| 56 |
+
"commonsense_qa": {
|
| 57 |
+
"alias": "commonsense_qa",
|
| 58 |
+
"acc,none": 0.5773955773955773,
|
| 59 |
+
"acc_stderr,none": 0.014142423233580207
|
| 60 |
+
},
|
| 61 |
+
"mmlu": {
|
| 62 |
+
"acc,none": 0.6324597635664435,
|
| 63 |
+
"acc_stderr,none": 0.0037954721741336904,
|
| 64 |
+
"alias": "mmlu"
|
| 65 |
+
},
|
| 66 |
+
"openbookqa": {
|
| 67 |
+
"alias": "openbookqa",
|
| 68 |
+
"acc,none": 0.368,
|
| 69 |
+
"acc_stderr,none": 0.021588982568353548,
|
| 70 |
+
"acc_norm,none": 0.47,
|
| 71 |
+
"acc_norm_stderr,none": 0.0223427481925028
|
| 72 |
+
},
|
| 73 |
+
"winogrande": {
|
| 74 |
+
"alias": "winogrande",
|
| 75 |
+
"acc,none": 0.7671665351223362,
|
| 76 |
+
"acc_stderr,none": 0.011878201073856598
|
| 77 |
+
},
|
| 78 |
+
"triviaqa": {
|
| 79 |
+
"alias": "triviaqa",
|
| 80 |
+
"exact_match,remove_whitespace": 0.595296477931342,
|
| 81 |
+
"exact_match_stderr,remove_whitespace": 0.003664271290957409
|
| 82 |
+
},
|
| 83 |
+
"truthfulqa_mc1": {
|
| 84 |
+
"alias": "truthfulqa_mc1",
|
| 85 |
+
"acc,none": 0.37821297429620565,
|
| 86 |
+
"acc_stderr,none": 0.016976335907546772
|
| 87 |
+
},
|
| 88 |
+
"truthfulqa_mc2": {
|
| 89 |
+
"alias": "truthfulqa_mc2",
|
| 90 |
+
"acc,none": 0.5284457708979753,
|
| 91 |
+
"acc_stderr,none": 0.015035693028473887
|
| 92 |
+
}
|
| 93 |
+
},
|
| 94 |
+
"Mistral-Nemo-Instruct-2407-NVFP4-4over6": {
|
| 95 |
+
"coqa": {
|
| 96 |
+
"alias": "coqa",
|
| 97 |
+
"em,none": 0.5498333333333334,
|
| 98 |
+
"em_stderr,none": 0.020187689512123422,
|
| 99 |
+
"f1,none": 0.7211863549140475,
|
| 100 |
+
"f1_stderr,none": 0.01540089217977273
|
| 101 |
+
},
|
| 102 |
+
"hellaswag": {
|
| 103 |
+
"alias": "hellaswag",
|
| 104 |
+
"acc,none": 0.619398526190002,
|
| 105 |
+
"acc_stderr,none": 0.004845424524763779,
|
| 106 |
+
"acc_norm,none": 0.8131846245767775,
|
| 107 |
+
"acc_norm_stderr,none": 0.003889666837869389
|
| 108 |
+
},
|
| 109 |
+
"ifeval": {
|
| 110 |
+
"alias": "ifeval",
|
| 111 |
+
"prompt_level_strict_acc,none": 0.4121996303142329,
|
| 112 |
+
"prompt_level_strict_acc_stderr,none": 0.021182238151733295,
|
| 113 |
+
"inst_level_strict_acc,none": 0.5095923261390888,
|
| 114 |
+
"inst_level_strict_acc_stderr,none": "N/A",
|
| 115 |
+
"prompt_level_loose_acc,none": 0.4824399260628466,
|
| 116 |
+
"prompt_level_loose_acc_stderr,none": 0.02150330051338897,
|
| 117 |
+
"inst_level_loose_acc,none": 0.5683453237410072,
|
| 118 |
+
"inst_level_loose_acc_stderr,none": "N/A"
|
| 119 |
+
},
|
| 120 |
+
"lambada_openai": {
|
| 121 |
+
"alias": "lambada_openai",
|
| 122 |
+
"perplexity,none": 2.954572513479153,
|
| 123 |
+
"perplexity_stderr,none": 0.054124688702298446,
|
| 124 |
+
"acc,none": 0.7686784397438385,
|
| 125 |
+
"acc_stderr,none": 0.0058747917899013785
|
| 126 |
+
},
|
| 127 |
+
"lambada_openai_cloze_yaml": {
|
| 128 |
+
"alias": "lambada_openai_cloze_yaml",
|
| 129 |
+
"perplexity,none": 30.035509240670926,
|
| 130 |
+
"perplexity_stderr,none": 0.7780223123588234,
|
| 131 |
+
"acc,none": 0.29827285076654375,
|
| 132 |
+
"acc_stderr,none": 0.006373868144287074
|
| 133 |
+
},
|
| 134 |
+
"lambada_standard": {
|
| 135 |
+
"alias": "lambada_standard",
|
| 136 |
+
"perplexity,none": 3.660039154584711,
|
| 137 |
+
"perplexity_stderr,none": 0.07563902292271452,
|
| 138 |
+
"acc,none": 0.6906656316708714,
|
| 139 |
+
"acc_stderr,none": 0.006439617662597691
|
| 140 |
+
},
|
| 141 |
+
"lambada_standard_cloze_yaml": {
|
| 142 |
+
"alias": "lambada_standard_cloze_yaml",
|
| 143 |
+
"perplexity,none": 40.99251979932923,
|
| 144 |
+
"perplexity_stderr,none": 1.0271212425445286,
|
| 145 |
+
"acc,none": 0.24665243547448087,
|
| 146 |
+
"acc_stderr,none": 0.006005545631215194
|
| 147 |
+
},
|
| 148 |
+
"commonsense_qa": {
|
| 149 |
+
"alias": "commonsense_qa",
|
| 150 |
+
"acc,none": 0.5921375921375921,
|
| 151 |
+
"acc_stderr,none": 0.014069810259917194
|
| 152 |
+
},
|
| 153 |
+
"mmlu": {
|
| 154 |
+
"acc,none": 0.6364477994587665,
|
| 155 |
+
"acc_stderr,none": 0.003806377839571922,
|
| 156 |
+
"alias": "mmlu"
|
| 157 |
+
},
|
| 158 |
+
"openbookqa": {
|
| 159 |
+
"alias": "openbookqa",
|
| 160 |
+
"acc,none": 0.392,
|
| 161 |
+
"acc_stderr,none": 0.02185468495561119,
|
| 162 |
+
"acc_norm,none": 0.472,
|
| 163 |
+
"acc_norm_stderr,none": 0.022347949832668024
|
| 164 |
+
},
|
| 165 |
+
"winogrande": {
|
| 166 |
+
"alias": "winogrande",
|
| 167 |
+
"acc,none": 0.755327545382794,
|
| 168 |
+
"acc_stderr,none": 0.012082125654159727
|
| 169 |
+
},
|
| 170 |
+
"triviaqa": {
|
| 171 |
+
"alias": "triviaqa",
|
| 172 |
+
"exact_match,remove_whitespace": 0.6011480160499332,
|
| 173 |
+
"exact_match_stderr,remove_whitespace": 0.003655519111850352
|
| 174 |
+
},
|
| 175 |
+
"truthfulqa_mc1": {
|
| 176 |
+
"alias": "truthfulqa_mc1",
|
| 177 |
+
"acc,none": 0.38310893512851896,
|
| 178 |
+
"acc_stderr,none": 0.017018461679389734
|
| 179 |
+
},
|
| 180 |
+
"truthfulqa_mc2": {
|
| 181 |
+
"alias": "truthfulqa_mc2",
|
| 182 |
+
"acc,none": 0.5367421440427503,
|
| 183 |
+
"acc_stderr,none": 0.01489354828588867
|
| 184 |
+
}
|
| 185 |
+
}
|
| 186 |
+
"Mistral-Nemo-Instruct-2407-NVFP4-FP8-RTN": {
|
| 187 |
+
"coqa": {
|
| 188 |
+
"alias": "coqa",
|
| 189 |
+
"em,none": 0.5683333333333334,
|
| 190 |
+
"em_stderr,none": 0.019596946262820592,
|
| 191 |
+
"f1,none": 0.7401341567024432,
|
| 192 |
+
"f1_stderr,none": 0.014222135053403443
|
| 193 |
+
},
|
| 194 |
+
"hellaswag": {
|
| 195 |
+
"alias": "hellaswag",
|
| 196 |
+
"acc,none": 0.6237801234813782,
|
| 197 |
+
"acc_stderr,none": 0.004834461997944986,
|
| 198 |
+
"acc_norm,none": 0.813981278629755,
|
| 199 |
+
"acc_norm_stderr,none": 0.003883265210791469
|
| 200 |
+
},
|
| 201 |
+
"ifeval": {
|
| 202 |
+
"alias": "ifeval",
|
| 203 |
+
"prompt_level_strict_acc,none": 0.39926062846580407,
|
| 204 |
+
"prompt_level_strict_acc_stderr,none": 0.021075331332701258,
|
| 205 |
+
"inst_level_strict_acc,none": 0.5011990407673861,
|
| 206 |
+
"inst_level_strict_acc_stderr,none": "N/A",
|
| 207 |
+
"prompt_level_loose_acc,none": 0.46210720887245843,
|
| 208 |
+
"prompt_level_loose_acc_stderr,none": 0.021454695436204742,
|
| 209 |
+
"inst_level_loose_acc,none": 0.5563549160671463,
|
| 210 |
+
"inst_level_loose_acc_stderr,none": "N/A"
|
| 211 |
+
},
|
| 212 |
+
"lambada_openai": {
|
| 213 |
+
"alias": "lambada_openai",
|
| 214 |
+
"perplexity,none": 2.959118986596569,
|
| 215 |
+
"perplexity_stderr,none": 0.05562968630849542,
|
| 216 |
+
"acc,none": 0.7618862798369882,
|
| 217 |
+
"acc_stderr,none": 0.005934024831865026
|
| 218 |
+
},
|
| 219 |
+
"lambada_openai_cloze_yaml": {
|
| 220 |
+
"alias": "lambada_openai_cloze_yaml",
|
| 221 |
+
"perplexity,none": 26.696978874621955,
|
| 222 |
+
"perplexity_stderr,none": 0.683775381967173,
|
| 223 |
+
"acc,none": 0.33145740345429847,
|
| 224 |
+
"acc_stderr,none": 0.006558287884402134
|
| 225 |
+
},
|
| 226 |
+
"lambada_standard": {
|
| 227 |
+
"alias": "lambada_standard",
|
| 228 |
+
"perplexity,none": 3.492972951792885,
|
| 229 |
+
"perplexity_stderr,none": 0.0721179626815854,
|
| 230 |
+
"acc,none": 0.6970696681544731,
|
| 231 |
+
"acc_stderr,none": 0.006402086620816973
|
| 232 |
+
},
|
| 233 |
+
"lambada_standard_cloze_yaml": {
|
| 234 |
+
"alias": "lambada_standard_cloze_yaml",
|
| 235 |
+
"perplexity,none": 37.411029419339414,
|
| 236 |
+
"perplexity_stderr,none": 0.9371152123007664,
|
| 237 |
+
"acc,none": 0.2582961381719387,
|
| 238 |
+
"acc_stderr,none": 0.0060979842659205745
|
| 239 |
+
},
|
| 240 |
+
"commonsense_qa": {
|
| 241 |
+
"alias": "commonsense_qa",
|
| 242 |
+
"acc,none": 0.6060606060606061,
|
| 243 |
+
"acc_stderr,none": 0.013989198052984327
|
| 244 |
+
},
|
| 245 |
+
"mmlu": {
|
| 246 |
+
"acc,none": 0.6434268622703319,
|
| 247 |
+
"acc_stderr,none": 0.0037824170513249015,
|
| 248 |
+
"alias": "mmlu"
|
| 249 |
+
},
|
| 250 |
+
"openbookqa": {
|
| 251 |
+
"alias": "openbookqa",
|
| 252 |
+
"acc,none": 0.404,
|
| 253 |
+
"acc_stderr,none": 0.021966635293832883,
|
| 254 |
+
"acc_norm,none": 0.478,
|
| 255 |
+
"acc_norm_stderr,none": 0.02236139673920787
|
| 256 |
+
},
|
| 257 |
+
"winogrande": {
|
| 258 |
+
"alias": "winogrande",
|
| 259 |
+
"acc,none": 0.7513812154696132,
|
| 260 |
+
"acc_stderr,none": 0.012147314713403173
|
| 261 |
+
},
|
| 262 |
+
"triviaqa": {
|
| 263 |
+
"alias": "triviaqa",
|
| 264 |
+
"exact_match,remove_whitespace": 0.6104547481052163,
|
| 265 |
+
"exact_match_stderr,remove_whitespace": 0.0036404759558834486
|
| 266 |
+
},
|
| 267 |
+
"truthfulqa_mc1": {
|
| 268 |
+
"alias": "truthfulqa_mc1",
|
| 269 |
+
"acc,none": 0.38922888616891066,
|
| 270 |
+
"acc_stderr,none": 0.01706855268069044
|
| 271 |
+
},
|
| 272 |
+
"truthfulqa_mc2": {
|
| 273 |
+
"alias": "truthfulqa_mc2",
|
| 274 |
+
"acc,none": 0.5389966378633866,
|
| 275 |
+
"acc_stderr,none": 0.015062753562771725
|
| 276 |
+
}
|
| 277 |
+
}
|
| 278 |
+
"Mistral-Nemo-Instruct-2407-NVFP4-FP8": {
|
| 279 |
+
"coqa": {
|
| 280 |
+
"alias": "coqa",
|
| 281 |
+
"em,none": 0.5733333333333334,
|
| 282 |
+
"em_stderr,none": 0.019505122108457063,
|
| 283 |
+
"f1,none": 0.7346963191068078,
|
| 284 |
+
"f1_stderr,none": 0.015019925951016882
|
| 285 |
+
},
|
| 286 |
+
"hellaswag": {
|
| 287 |
+
"alias": "hellaswag",
|
| 288 |
+
"acc,none": 0.6239792869946226,
|
| 289 |
+
"acc_stderr,none": 0.004833953712521647,
|
| 290 |
+
"acc_norm,none": 0.8124875522804222,
|
| 291 |
+
"acc_norm_stderr,none": 0.0038952463204528333
|
| 292 |
+
},
|
| 293 |
+
"ifeval": {
|
| 294 |
+
"alias": "ifeval",
|
| 295 |
+
"prompt_level_strict_acc,none": 0.4195933456561922,
|
| 296 |
+
"prompt_level_strict_acc_stderr,none": 0.021236532548855144,
|
| 297 |
+
"inst_level_strict_acc,none": 0.5107913669064749,
|
| 298 |
+
"inst_level_strict_acc_stderr,none": "N/A",
|
| 299 |
+
"prompt_level_loose_acc,none": 0.49168207024029575,
|
| 300 |
+
"prompt_level_loose_acc_stderr,none": 0.02151359656402127,
|
| 301 |
+
"inst_level_loose_acc,none": 0.5767386091127098,
|
| 302 |
+
"inst_level_loose_acc_stderr,none": "N/A"
|
| 303 |
+
},
|
| 304 |
+
"lambada_openai": {
|
| 305 |
+
"alias": "lambada_openai",
|
| 306 |
+
"perplexity,none": 2.923326330881571,
|
| 307 |
+
"perplexity_stderr,none": 0.05419037402311029,
|
| 308 |
+
"acc,none": 0.7725596739763245,
|
| 309 |
+
"acc_stderr,none": 0.005839986255519642
|
| 310 |
+
},
|
| 311 |
+
"lambada_openai_cloze_yaml": {
|
| 312 |
+
"alias": "lambada_openai_cloze_yaml",
|
| 313 |
+
"perplexity,none": 26.694758918393248,
|
| 314 |
+
"perplexity_stderr,none": 0.6858369120887257,
|
| 315 |
+
"acc,none": 0.33165146516592275,
|
| 316 |
+
"acc_stderr,none": 0.0065592552732574244
|
| 317 |
+
},
|
| 318 |
+
"lambada_standard": {
|
| 319 |
+
"alias": "lambada_standard",
|
| 320 |
+
"perplexity,none": 3.551356285449324,
|
| 321 |
+
"perplexity_stderr,none": 0.07342709527808654,
|
| 322 |
+
"acc,none": 0.6926062487871143,
|
| 323 |
+
"acc_stderr,none": 0.006428398527904964
|
| 324 |
+
},
|
| 325 |
+
"lambada_standard_cloze_yaml": {
|
| 326 |
+
"alias": "lambada_standard_cloze_yaml",
|
| 327 |
+
"perplexity,none": 35.56146784383732,
|
| 328 |
+
"perplexity_stderr,none": 0.8740618781960072,
|
| 329 |
+
"acc,none": 0.2837182223947215,
|
| 330 |
+
"acc_stderr,none": 0.0062805494483705775
|
| 331 |
+
},
|
| 332 |
+
"commonsense_qa": {
|
| 333 |
+
"alias": "commonsense_qa",
|
| 334 |
+
"acc,none": 0.6208026208026208,
|
| 335 |
+
"acc_stderr,none": 0.013890872306969766
|
| 336 |
+
},
|
| 337 |
+
"mmlu": {
|
| 338 |
+
"acc,none": 0.6454208802164934,
|
| 339 |
+
"acc_stderr,none": 0.0037774970297410814,
|
| 340 |
+
"alias": "mmlu"
|
| 341 |
+
},
|
| 342 |
+
"openbookqa": {
|
| 343 |
+
"alias": "openbookqa",
|
| 344 |
+
"acc,none": 0.404,
|
| 345 |
+
"acc_stderr,none": 0.021966635293832883,
|
| 346 |
+
"acc_norm,none": 0.488,
|
| 347 |
+
"acc_norm_stderr,none": 0.022376626797927058
|
| 348 |
+
},
|
| 349 |
+
"winogrande": {
|
| 350 |
+
"alias": "winogrande",
|
| 351 |
+
"acc,none": 0.7545382794001578,
|
| 352 |
+
"acc_stderr,none": 0.01209527293718361
|
| 353 |
+
},
|
| 354 |
+
"triviaqa": {
|
| 355 |
+
"alias": "triviaqa",
|
| 356 |
+
"exact_match,remove_whitespace": 0.6184239857333927,
|
| 357 |
+
"exact_match_stderr,remove_whitespace": 0.003626487357735664
|
| 358 |
+
},
|
| 359 |
+
"truthfulqa_mc1": {
|
| 360 |
+
"alias": "truthfulqa_mc1",
|
| 361 |
+
"acc,none": 0.39167686658506734,
|
| 362 |
+
"acc_stderr,none": 0.017087795881769625
|
| 363 |
+
},
|
| 364 |
+
"truthfulqa_mc2": {
|
| 365 |
+
"alias": "truthfulqa_mc2",
|
| 366 |
+
"acc,none": 0.5475484445657804,
|
| 367 |
+
"acc_stderr,none": 0.015041357055984873
|
| 368 |
+
}
|
| 369 |
+
}
|
| 370 |
+
}
|