File size: 24,025 Bytes
d0f4700 2883125 bd61800 d0f4700 bd61800 8d0ccc4 bd61800 2883125 7920348 d0f4700 7920348 d0f4700 7920348 d0f4700 7920348 a619d18 7920348 d0f4700 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 |
---
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
tags:
- merge
- moe
- biology
- medical
- MoE
- genetic
---
## Description
3 Models used in this merge of 4x7B:
- [cognitivecomputations/WestLake-7B-v2-laser](https://huggingface.co/cognitivecomputations/WestLake-7B-v2-laser)
- [mlabonne/Daredevil-7B](https://huggingface.co/mlabonne/Daredevil-7B) (used twice! initially chose another model, but using it twice worked better somehow.)
- [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B)
This is a MoE of top 4x 7B models including BioMistral-7B. Here is the comparison between the two:
| Metric | BioMistral-7B | Bioxtral-4x7B-v0.1 |
|-----------------------------|---------------|--------------------|
| **Average** | 54.99 | **70.84** |
| ARC | 54.27 | **68.34** |
| HellaSwag | 79.09 | **87.27** |
| TruthfulQA | 51.61 | **68.45** |
| Winogrande | 73.48 | **82.90** |
| GSM8K | 0 | **56.63** |
| Professional Medicine | 55.51 | **67.3** |
| College Medicine | 58.96 | **61.84** |
| Medical Genetics | 67.00 | **74.0** |
## How to use it
```python
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="MaziyarPanahi/Bioxtral-4x7B-v0.1")
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Bioxtral-4x7B-v0.1")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Bioxtral-4x7B-v0.1")
```
## Quantized mode
Here is the list of GGUF models quantized from 2 to 8 bits: https://huggingface.co/MaziyarPanahi/Bioxtral-4x7B-v0.1-GGUF
## Examples
A 23-year-old pregnant woman at 22 weeks gestation presents with burning upon urination. She states it started 1 day ago and has been worsening despite drinking more water and taking cranberry extract. She otherwise feels well and is followed by a doctor for her pregnancy. Her temperature is 97.7°F (36.5°C), blood pressure is 122/77 mmHg, pulse is 80/min, respirations are 19/min, and oxygen saturation is 98% on room air. Physical exam is notable for an absence of costovertebral angle tenderness and a gravid uterus. Which of the following is the best treatment for this patient?
{ "A": "Ampicillin", "B": "Ceftriaxone", "C": "Doxycycline", "D": "Nitrofurantoin" }
```
The best treatment option for this patient would be **D: Nitrofurantoin**. This choice is in accordance with current guidelines recommending nitrofurantoin as the first line agent for uncomplicated lower UTI during pregnancy due to its safety profile. Although ampicillin and ceftriaxone may also be used if there is concern for pyelonephritis or resistance, they should generally be reserved for more severe cases. Doxycycline is contraindicated in pregnancy.</s>
```
A 67-year-old woman with advanced bladder cancer comes to the physician for a follow-up examination. She is currently undergoing chemotherapy with an agent that forms cross-links between DNA strands. Serum studies show a creatinine concentration of 2.1 mg/dL and a blood urea nitrogen concentration of 30 mg/dL. Urine dipstick of a clean-catch midstream specimen shows 2+ protein and 1+ glucose. Prior to initiation of chemotherapy, her laboratory values were within the reference range. In addition to hydration, administration of which of the following would most likely have prevented this patient's current condition?
{ "A": "Mesna", "B": "Amifostine", "C": "Rasburicase", "D": "Leucovorin" }
```
B: Amifostine</s>
```
describe about pros and cons of docker system.
```
Answer:
Docker is an open-source platform for developing, shipping, and running applications by using containers. Like all technologies, Docker has its advantages and disadvantages. Here are some key points on both sides:
Pros (Advantages) of Docker:
1. **Portability**: One of the main benefits of Docker is its ability to create portable containers holding an application with all its dependencies. This makes it easy to run the same application consistently across different environments such as development, testing, and production.
2. **Efficiency**: Containers are lightweight and use resources efficiently compared to virtual machines. This allows more applications to be hosted on a single server.
3. **Simplified deployment**: With Docker, developers can package their code along with all its dependencies into a container which can then be deployed easily without worrying about compatibility issues.
4. **Improved collaboration**: Docker provides tools like Docker Hub which allow developers to share their images publicly or privately. This promotes collaboration among teams working on the same project.
5. **Automation**: Docker integrates well with many continuous integration and delivery systems, making it easier to automate the building, testing, and deploying of applications.
Cons (Disadvantages) of Docker:
1. **Steep learning curve**: For those new to containerization technology, there may be a significant learning curve involved in understanding how Docker works and mastering its commands.
2. **Additional management overhead**: Managing Docker containers requires additional effort compared to traditional methods. This includes tasks like monitoring, scaling, and orchestrating containers.
3. **Potential security risks**: While Docker itself is secure, improper configuration of containers could lead to potential vulnerabilities. It’s important to follow best practices when creating and managing containers.
4. **Vendor lock-in**: Although Docker is open source, if your organization relies heavily on proprietary extensions from Docker Inc., switching to another solution might become difficult.
5. **Limited storage**: Each container has its own file system, so storing large amounts of data within the container can be challenging. To address this issue, Docker Volumes were introduced but they require separate management.</s>
```
Hi, I need to get from New York to Los Angeles. Can you help me with that?
```
```tool_call
{
"arguments": {"origin": "New York", "destination": "Los Angeles", "mode": ""},
"name": "get_directions"
}
```</s>
```
There are three killers in a room. Someone enters the room and kills one of them. Nobody leaves the room. How many killers are left in the room? Explain your reasoning step by step.
```
1. Initially, there are three killers in the room.
2. Then, someone else comes into the room and kills one of these three killers.
3. However, this "someone" is also considered as a person or killer (since they committed an act of killing).
4. So after the event, we have four people in total - the remaining two original killers plus the newcomer who killed one of the initial killers.
5. But since our question asks for the number of killers, we should only count those who were originally killers before anyone acted.
6. Therefore, there are still two killers left in the room.
```
Answer should be 3, the new person walking in is also a killer!
Mark is faster than Mary , Mary is faster than Joe. Is Joe faster than Mark? Let's think step by step
```
Let's analyze the given statements one by one:
1. Mark is faster than Mary.
2. Mary is faster than Joe.
Now, let's try to determine the relative speeds of all three individuals based on these statements:
- From statement 1, we know that Mark has a higher speed compared to Mary.
- From statement 2, we know that Mary has a higher speed compared to Joe.
Combining both pieces of information, we can conclude that Mark must have the highest speed among the three (since he is faster than Mary and Mary is faster than Joe). Therefore, Joe is not faster than Mark.</s>
```
If I lay 2 wet shirts out in the sun flat on the ground to dry and it takes 5 hours until they are dry, how long would it take to dry 4 shirts of the same type that way simultanously?
```
Assuming that the drying process is not limited by any other factor than the surface area exposed to the sunlight, we can use a simple proportionality argument.
If 2 shirts take 5 hours to dry when laid flat on the ground, then the combined surface area of these two shirts is equivalent to the drying time of 5 hours. Let's call this surface area equivalent to 5 "drying-hours per unit area."
Now, if we have 4 shirts of the same type and we lay them all flat on the ground at the same time, their combined surface area will be greater than that of the two previously dried shirts. However, since they are all of the same type, we can assume that the ratio of their surface areas to the drying time of 5 hours remains constant. In other words, the 4 new shirts will also have a surface area equivalent to 5 "drying-hours per unit area."
To find out how long it would take for these 4 shirts to dry simultaneously, we need to divide the total drying time (5 hours) by the number of shirts (4). This gives us:
Drying time for 4 shirts = Total drying time / Number of shirts
= 5 hours / 4
= 1.25 hours per shirt
So, it would take approximately 1 hour and 15 minutes (or 75 minutes) for the 4 shirts to dry simultaneously under the same conditions as the original 2 shirts.</s>
```
Wow! Way to go to be wrong! It's the same, they are drying not baking!
explain step by step 25-4*2+3=?
```
Step 1: Identify the multiplication operation first. In this case, it is "4 * 2".
Step 2: Perform the multiplication. Multiplying 4 and 2 gives you 8.
Step 3: Now we have the expression "25 - 8 + 3".
Step 4: Solve the subtraction next. Subtracting 8 from 25 gives you 17.
Step 5: Finally, add 3 to the result of the previous step. Adding 3 to 17 gives you a final answer of 20.
So, 25 - 4 * 2 + 3 = 20.</s>
```
## Eval
source: https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__Bioxtral-4x7B-v0.1
```python
{
"all": {
"acc": 0.6390815384774987,
"acc_stderr": 0.03233527173865626,
"acc_norm": 0.6405373328568302,
"acc_norm_stderr": 0.032994557880045274,
"mc1": 0.5152998776009792,
"mc1_stderr": 0.017495304473187902,
"mc2": 0.6845419346695587,
"mc2_stderr": 0.014829461272743373
},
"harness|arc:challenge|25": {
"acc": 0.658703071672355,
"acc_stderr": 0.01385583128749772,
"acc_norm": 0.6834470989761092,
"acc_norm_stderr": 0.013592431519068079
},
"harness|hellaswag|10": {
"acc": 0.6946823341963753,
"acc_stderr": 0.004596006250433548,
"acc_norm": 0.8727345150368453,
"acc_norm_stderr": 0.003325890225529856
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.31,
"acc_stderr": 0.04648231987117316,
"acc_norm": 0.31,
"acc_norm_stderr": 0.04648231987117316
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6370370370370371,
"acc_stderr": 0.04153948404742397,
"acc_norm": 0.6370370370370371,
"acc_norm_stderr": 0.04153948404742397
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.7105263157894737,
"acc_stderr": 0.03690677986137283,
"acc_norm": 0.7105263157894737,
"acc_norm_stderr": 0.03690677986137283
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.63,
"acc_stderr": 0.04852365870939099,
"acc_norm": 0.63,
"acc_norm_stderr": 0.04852365870939099
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.6943396226415094,
"acc_stderr": 0.028353298073322663,
"acc_norm": 0.6943396226415094,
"acc_norm_stderr": 0.028353298073322663
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7222222222222222,
"acc_stderr": 0.037455547914624555,
"acc_norm": 0.7222222222222222,
"acc_norm_stderr": 0.037455547914624555
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.44,
"acc_stderr": 0.04988876515698589,
"acc_norm": 0.44,
"acc_norm_stderr": 0.04988876515698589
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.56,
"acc_stderr": 0.049888765156985884,
"acc_norm": 0.56,
"acc_norm_stderr": 0.049888765156985884
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.29,
"acc_stderr": 0.04560480215720684,
"acc_norm": 0.29,
"acc_norm_stderr": 0.04560480215720684
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6184971098265896,
"acc_stderr": 0.03703851193099521,
"acc_norm": 0.6184971098265896,
"acc_norm_stderr": 0.03703851193099521
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.43137254901960786,
"acc_stderr": 0.04928099597287534,
"acc_norm": 0.43137254901960786,
"acc_norm_stderr": 0.04928099597287534
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.78,
"acc_stderr": 0.041633319989322605,
"acc_norm": 0.78,
"acc_norm_stderr": 0.041633319989322605
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5829787234042553,
"acc_stderr": 0.03223276266711712,
"acc_norm": 0.5829787234042553,
"acc_norm_stderr": 0.03223276266711712
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.45614035087719296,
"acc_stderr": 0.04685473041907789,
"acc_norm": 0.45614035087719296,
"acc_norm_stderr": 0.04685473041907789
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5310344827586206,
"acc_stderr": 0.04158632762097828,
"acc_norm": 0.5310344827586206,
"acc_norm_stderr": 0.04158632762097828
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.42328042328042326,
"acc_stderr": 0.025446365634406786,
"acc_norm": 0.42328042328042326,
"acc_norm_stderr": 0.025446365634406786
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.47619047619047616,
"acc_stderr": 0.04467062628403273,
"acc_norm": 0.47619047619047616,
"acc_norm_stderr": 0.04467062628403273
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.28,
"acc_stderr": 0.04512608598542128,
"acc_norm": 0.28,
"acc_norm_stderr": 0.04512608598542128
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7516129032258064,
"acc_stderr": 0.024580028921481003,
"acc_norm": 0.7516129032258064,
"acc_norm_stderr": 0.024580028921481003
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.4975369458128079,
"acc_stderr": 0.03517945038691063,
"acc_norm": 0.4975369458128079,
"acc_norm_stderr": 0.03517945038691063
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.65,
"acc_stderr": 0.047937248544110196,
"acc_norm": 0.65,
"acc_norm_stderr": 0.047937248544110196
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7757575757575758,
"acc_stderr": 0.032568666616811015,
"acc_norm": 0.7757575757575758,
"acc_norm_stderr": 0.032568666616811015
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.7878787878787878,
"acc_stderr": 0.029126522834586815,
"acc_norm": 0.7878787878787878,
"acc_norm_stderr": 0.029126522834586815
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.8808290155440415,
"acc_stderr": 0.02338193534812142,
"acc_norm": 0.8808290155440415,
"acc_norm_stderr": 0.02338193534812142
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6666666666666666,
"acc_stderr": 0.02390115797940254,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.02390115797940254
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.3333333333333333,
"acc_stderr": 0.028742040903948485,
"acc_norm": 0.3333333333333333,
"acc_norm_stderr": 0.028742040903948485
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6890756302521008,
"acc_stderr": 0.030066761582977927,
"acc_norm": 0.6890756302521008,
"acc_norm_stderr": 0.030066761582977927
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.36423841059602646,
"acc_stderr": 0.03929111781242742,
"acc_norm": 0.36423841059602646,
"acc_norm_stderr": 0.03929111781242742
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8165137614678899,
"acc_stderr": 0.01659525971039931,
"acc_norm": 0.8165137614678899,
"acc_norm_stderr": 0.01659525971039931
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5,
"acc_stderr": 0.034099716973523674,
"acc_norm": 0.5,
"acc_norm_stderr": 0.034099716973523674
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.803921568627451,
"acc_stderr": 0.027865942286639318,
"acc_norm": 0.803921568627451,
"acc_norm_stderr": 0.027865942286639318
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.7932489451476793,
"acc_stderr": 0.02636165166838909,
"acc_norm": 0.7932489451476793,
"acc_norm_stderr": 0.02636165166838909
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6816143497757847,
"acc_stderr": 0.03126580522513713,
"acc_norm": 0.6816143497757847,
"acc_norm_stderr": 0.03126580522513713
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7480916030534351,
"acc_stderr": 0.03807387116306085,
"acc_norm": 0.7480916030534351,
"acc_norm_stderr": 0.03807387116306085
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7851239669421488,
"acc_stderr": 0.037494924487096966,
"acc_norm": 0.7851239669421488,
"acc_norm_stderr": 0.037494924487096966
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.7314814814814815,
"acc_stderr": 0.042844679680521934,
"acc_norm": 0.7314814814814815,
"acc_norm_stderr": 0.042844679680521934
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7484662576687117,
"acc_stderr": 0.03408997886857529,
"acc_norm": 0.7484662576687117,
"acc_norm_stderr": 0.03408997886857529
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.44642857142857145,
"acc_stderr": 0.047184714852195886,
"acc_norm": 0.44642857142857145,
"acc_norm_stderr": 0.047184714852195886
},
"harness|hendrycksTest-management|5": {
"acc": 0.7669902912621359,
"acc_stderr": 0.04185832598928315,
"acc_norm": 0.7669902912621359,
"acc_norm_stderr": 0.04185832598928315
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8717948717948718,
"acc_stderr": 0.02190190511507333,
"acc_norm": 0.8717948717948718,
"acc_norm_stderr": 0.02190190511507333
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.74,
"acc_stderr": 0.04408440022768079,
"acc_norm": 0.74,
"acc_norm_stderr": 0.04408440022768079
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8186462324393359,
"acc_stderr": 0.013778693778464074,
"acc_norm": 0.8186462324393359,
"acc_norm_stderr": 0.013778693778464074
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7254335260115607,
"acc_stderr": 0.02402774515526502,
"acc_norm": 0.7254335260115607,
"acc_norm_stderr": 0.02402774515526502
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.47374301675977654,
"acc_stderr": 0.016699427672784768,
"acc_norm": 0.47374301675977654,
"acc_norm_stderr": 0.016699427672784768
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7058823529411765,
"acc_stderr": 0.026090162504279053,
"acc_norm": 0.7058823529411765,
"acc_norm_stderr": 0.026090162504279053
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7009646302250804,
"acc_stderr": 0.02600330111788514,
"acc_norm": 0.7009646302250804,
"acc_norm_stderr": 0.02600330111788514
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7098765432098766,
"acc_stderr": 0.025251173936495033,
"acc_norm": 0.7098765432098766,
"acc_norm_stderr": 0.025251173936495033
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.4645390070921986,
"acc_stderr": 0.02975238965742705,
"acc_norm": 0.4645390070921986,
"acc_norm_stderr": 0.02975238965742705
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.42894393741851367,
"acc_stderr": 0.012640625443067358,
"acc_norm": 0.42894393741851367,
"acc_norm_stderr": 0.012640625443067358
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6727941176470589,
"acc_stderr": 0.028501452860396553,
"acc_norm": 0.6727941176470589,
"acc_norm_stderr": 0.028501452860396553
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6437908496732027,
"acc_stderr": 0.019373332420724507,
"acc_norm": 0.6437908496732027,
"acc_norm_stderr": 0.019373332420724507
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.7090909090909091,
"acc_stderr": 0.04350271442923243,
"acc_norm": 0.7090909090909091,
"acc_norm_stderr": 0.04350271442923243
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.7061224489795919,
"acc_stderr": 0.02916273841024977,
"acc_norm": 0.7061224489795919,
"acc_norm_stderr": 0.02916273841024977
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8009950248756219,
"acc_stderr": 0.028231365092758406,
"acc_norm": 0.8009950248756219,
"acc_norm_stderr": 0.028231365092758406
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.88,
"acc_stderr": 0.03265986323710906,
"acc_norm": 0.88,
"acc_norm_stderr": 0.03265986323710906
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5542168674698795,
"acc_stderr": 0.03869543323472101,
"acc_norm": 0.5542168674698795,
"acc_norm_stderr": 0.03869543323472101
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8362573099415205,
"acc_stderr": 0.028380919596145866,
"acc_norm": 0.8362573099415205,
"acc_norm_stderr": 0.028380919596145866
},
"harness|truthfulqa:mc|0": {
"mc1": 0.5152998776009792,
"mc1_stderr": 0.017495304473187902,
"mc2": 0.6845419346695587,
"mc2_stderr": 0.014829461272743373
},
"harness|winogrande|5": {
"acc": 0.8287292817679558,
"acc_stderr": 0.010588417294962524
},
"harness|gsm8k|5": {
"acc": 0.5663381349507203,
"acc_stderr": 0.013650728047064688
}
}
``` |