Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
Commit
•
6d0d93c
1
Parent(s):
601f2e9
Add type to more models (#140)
Browse files- Add type to more models (867146db84fc40a6a995e5754fa90d202fddd201)
Co-authored-by: Apolinário from multimodal AI art <multimodalart@users.noreply.huggingface.co>
src/auto_leaderboard/model_metadata_type.py
CHANGED
@@ -28,6 +28,8 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
28 |
"aisquared/dlite-v2-1_5b": ModelType.SFT,
|
29 |
"aisquared/chopt-1_3b": ModelType.SFT,
|
30 |
"aisquared/dlite-v2-355m": ModelType.SFT,
|
|
|
|
|
31 |
"TheBloke/tulu-7B-fp16": ModelType.SFT,
|
32 |
"TheBloke/guanaco-7B-HF": ModelType.SFT,
|
33 |
"TheBloke/koala-7B-HF": ModelType.SFT,
|
@@ -43,13 +45,17 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
43 |
"TheBloke/OpenAssistant-SFT-7-Llama-30B-HF": ModelType.SFT,
|
44 |
"TheBloke/vicuna-13B-1.1-HF": ModelType.SFT,
|
45 |
"TheBloke/guanaco-13B-HF": ModelType.SFT,
|
|
|
46 |
"TheBloke/airoboros-7b-gpt4-fp16": ModelType.SFT,
|
47 |
"TheBloke/Llama-2-13B-fp16": ModelType.PT,
|
|
|
48 |
"TheBloke/Planner-7B-fp16": ModelType.SFT,
|
49 |
"TheBloke/Wizard-Vicuna-13B-Uncensored-HF": ModelType.SFT,
|
50 |
"TheBloke/gpt4-alpaca-lora-13B-HF": ModelType.SFT,
|
51 |
"TheBloke/gpt4-x-vicuna-13B-HF": ModelType.SFT,
|
|
|
52 |
"TheBloke/tulu-13B-fp16": ModelType.SFT,
|
|
|
53 |
"jphme/orca_mini_v2_ger_7b": ModelType.SFT,
|
54 |
"Ejafa/vicuna_7B_vanilla_1.1": ModelType.SFT,
|
55 |
"kevinpro/Vicuna-13B-CoT": ModelType.SFT,
|
@@ -216,9 +222,9 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
216 |
"pythainlp/wangchanglm-7.5B-sft-enth": ModelType.SFT,
|
217 |
"pythainlp/wangchanglm-7.5B-sft-en-sharded": ModelType.SFT,
|
218 |
"euclaise/gpt-neox-122m-minipile-digits": ModelType.SFT,
|
219 |
-
"stabilityai/
|
220 |
"stabilityai/stablelm-tuned-alpha-7b": ModelType.SFT,
|
221 |
-
"stabilityai/
|
222 |
"stabilityai/stablelm-base-alpha-7b": ModelType.PT,
|
223 |
"stabilityai/stablelm-base-alpha-3b": ModelType.PT,
|
224 |
"stabilityai/stablelm-tuned-alpha-3b": ModelType.SFT,
|
@@ -360,6 +366,7 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
360 |
"SebastianSchramm/Cerebras-GPT-111M-instruction": ModelType.SFT,
|
361 |
"victor123/WizardLM-13B-1.0": ModelType.SFT,
|
362 |
"OpenBuddy/openbuddy-openllama-13b-v7-fp16": ModelType.SFT,
|
|
|
363 |
"baichuan-inc/Baichuan-7B": ModelType.PT,
|
364 |
"tiiuae/falcon-40b-instruct": ModelType.SFT,
|
365 |
"tiiuae/falcon-40b": ModelType.PT,
|
@@ -368,8 +375,9 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
368 |
"YeungNLP/firefly-llama-13b-v1.2": ModelType.SFT,
|
369 |
"YeungNLP/firefly-ziya-13b": ModelType.SFT,
|
370 |
"shaohang/Sparse0.5_OPT-1.3": ModelType.SFT,
|
371 |
-
"
|
372 |
"xzuyn/MedicWizard-7B": ModelType.SFT,
|
|
|
373 |
"beomi/KoAlpaca-Polyglot-5.8B": ModelType.SFT,
|
374 |
"beomi/llama-2-ko-7b": ModelType.SFT,
|
375 |
"Salesforce/codegen-6B-multi": ModelType.PT,
|
@@ -379,16 +387,18 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
379 |
"gpt2-large": ModelType.PT,
|
380 |
"frank098/orca_mini_3b_juniper": ModelType.SFT,
|
381 |
"frank098/WizardLM_13B_juniper": ModelType.SFT,
|
|
|
382 |
"huggingface/llama-13b": ModelType.PT,
|
383 |
"huggingface/llama-7b": ModelType.PT,
|
384 |
"huggingface/llama-65b": ModelType.PT,
|
385 |
"huggingface/llama-65b": ModelType.PT,
|
386 |
"huggingface/llama-30b": ModelType.PT,
|
387 |
-
"
|
388 |
-
"
|
389 |
-
"
|
390 |
-
"
|
391 |
-
"
|
|
|
392 |
"ariellee/SuperPlatty-30B": ModelType.SFT,
|
393 |
"danielhanchen/open_llama_3b_600bt_preview": ModelType.SFT,
|
394 |
"cerebras/Cerebras-GPT-256M": ModelType.PT,
|
@@ -418,6 +428,7 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
418 |
"upstage/llama-30b-instruct-2048": ModelType.SFT,
|
419 |
"upstage/llama-30b-instruct": ModelType.SFT,
|
420 |
"WizardLM/WizardLM-13B-1.0": ModelType.SFT,
|
|
|
421 |
"WizardLM/WizardLM-30B-V1.0": ModelType.SFT,
|
422 |
"WizardLM/WizardCoder-15B-V1.0": ModelType.SFT,
|
423 |
"gpt2": ModelType.PT,
|
@@ -456,9 +467,12 @@ TYPE_METADATA: Dict[str, ModelType] = {
|
|
456 |
"h2oai/h2ogpt-gm-oasst1-en-1024-12b": ModelType.SFT,
|
457 |
"h2oai/h2ogpt-gm-oasst1-multilang-1024-20b": ModelType.SFT,
|
458 |
"bofenghuang/vigogne-13b-instruct": ModelType.SFT,
|
|
|
459 |
"Vmware/open-llama-7b-v2-open-instruct": ModelType.SFT,
|
460 |
"VMware/open-llama-0.7T-7B-open-instruct-v1.1": ModelType.SFT,
|
461 |
"ewof/koishi-instruct-3b": ModelType.SFT,
|
|
|
|
|
462 |
}
|
463 |
|
464 |
|
|
|
28 |
"aisquared/dlite-v2-1_5b": ModelType.SFT,
|
29 |
"aisquared/chopt-1_3b": ModelType.SFT,
|
30 |
"aisquared/dlite-v2-355m": ModelType.SFT,
|
31 |
+
"augtoma/qCammel-13": ModelType.SFT,
|
32 |
+
"TheBloke/alpaca-lora-65B-HF": ModelType.SFT,
|
33 |
"TheBloke/tulu-7B-fp16": ModelType.SFT,
|
34 |
"TheBloke/guanaco-7B-HF": ModelType.SFT,
|
35 |
"TheBloke/koala-7B-HF": ModelType.SFT,
|
|
|
45 |
"TheBloke/OpenAssistant-SFT-7-Llama-30B-HF": ModelType.SFT,
|
46 |
"TheBloke/vicuna-13B-1.1-HF": ModelType.SFT,
|
47 |
"TheBloke/guanaco-13B-HF": ModelType.SFT,
|
48 |
+
"TheBloke/guanaco-65B-HF": ModelType.SFT,
|
49 |
"TheBloke/airoboros-7b-gpt4-fp16": ModelType.SFT,
|
50 |
"TheBloke/Llama-2-13B-fp16": ModelType.PT,
|
51 |
+
"TheBloke/llama-2-70b-Guanaco-QLoRA-fp16": ModelType.SFT,
|
52 |
"TheBloke/Planner-7B-fp16": ModelType.SFT,
|
53 |
"TheBloke/Wizard-Vicuna-13B-Uncensored-HF": ModelType.SFT,
|
54 |
"TheBloke/gpt4-alpaca-lora-13B-HF": ModelType.SFT,
|
55 |
"TheBloke/gpt4-x-vicuna-13B-HF": ModelType.SFT,
|
56 |
+
"TheBloke/gpt4-alpaca-lora_mlp-65B-HF": ModelType.SFT,
|
57 |
"TheBloke/tulu-13B-fp16": ModelType.SFT,
|
58 |
+
"TheBloke/VicUnlocked-alpaca-65B-QLoRA-fp16": ModelType.SFT,
|
59 |
"jphme/orca_mini_v2_ger_7b": ModelType.SFT,
|
60 |
"Ejafa/vicuna_7B_vanilla_1.1": ModelType.SFT,
|
61 |
"kevinpro/Vicuna-13B-CoT": ModelType.SFT,
|
|
|
222 |
"pythainlp/wangchanglm-7.5B-sft-enth": ModelType.SFT,
|
223 |
"pythainlp/wangchanglm-7.5B-sft-en-sharded": ModelType.SFT,
|
224 |
"euclaise/gpt-neox-122m-minipile-digits": ModelType.SFT,
|
225 |
+
"stabilityai/StableBeluga1-Delta": ModelType.SFT,
|
226 |
"stabilityai/stablelm-tuned-alpha-7b": ModelType.SFT,
|
227 |
+
"stabilityai/StableBeluga2": ModelType.SFT,
|
228 |
"stabilityai/stablelm-base-alpha-7b": ModelType.PT,
|
229 |
"stabilityai/stablelm-base-alpha-3b": ModelType.PT,
|
230 |
"stabilityai/stablelm-tuned-alpha-3b": ModelType.SFT,
|
|
|
366 |
"SebastianSchramm/Cerebras-GPT-111M-instruction": ModelType.SFT,
|
367 |
"victor123/WizardLM-13B-1.0": ModelType.SFT,
|
368 |
"OpenBuddy/openbuddy-openllama-13b-v7-fp16": ModelType.SFT,
|
369 |
+
"OpenBuddyEA/openbuddy-llama-30b-v7.1-bf16": ModelType.SFT,
|
370 |
"baichuan-inc/Baichuan-7B": ModelType.PT,
|
371 |
"tiiuae/falcon-40b-instruct": ModelType.SFT,
|
372 |
"tiiuae/falcon-40b": ModelType.PT,
|
|
|
375 |
"YeungNLP/firefly-llama-13b-v1.2": ModelType.SFT,
|
376 |
"YeungNLP/firefly-ziya-13b": ModelType.SFT,
|
377 |
"shaohang/Sparse0.5_OPT-1.3": ModelType.SFT,
|
378 |
+
"xzuyn/Alpacino-SuperCOT-13B": ModelType.SFT,
|
379 |
"xzuyn/MedicWizard-7B": ModelType.SFT,
|
380 |
+
"xDAN-AI/xDAN_13b_l2_lora": ModelType.SFT,
|
381 |
"beomi/KoAlpaca-Polyglot-5.8B": ModelType.SFT,
|
382 |
"beomi/llama-2-ko-7b": ModelType.SFT,
|
383 |
"Salesforce/codegen-6B-multi": ModelType.PT,
|
|
|
387 |
"gpt2-large": ModelType.PT,
|
388 |
"frank098/orca_mini_3b_juniper": ModelType.SFT,
|
389 |
"frank098/WizardLM_13B_juniper": ModelType.SFT,
|
390 |
+
"FPHam/Free_Sydney_13b_HF": ModelType.SFT,
|
391 |
"huggingface/llama-13b": ModelType.PT,
|
392 |
"huggingface/llama-7b": ModelType.PT,
|
393 |
"huggingface/llama-65b": ModelType.PT,
|
394 |
"huggingface/llama-65b": ModelType.PT,
|
395 |
"huggingface/llama-30b": ModelType.PT,
|
396 |
+
"jondurbin/airoboros-13b-gpt4-1.4": ModelType.SFT,
|
397 |
+
"jondurbin/airoboros-7b": ModelType.SFT,
|
398 |
+
"jondurbin/airoboros-7b-gpt4-1.4": ModelType.SFT,
|
399 |
+
"jondurbin/airoboros-l2-70b-gpt4-1.4.1": ModelType.SFT,
|
400 |
+
"jondurbin/airoboros-13b": ModelType.SFT,
|
401 |
+
"jondurbin/airoboros-65b-gpt4-1.2": ModelType.SFT,
|
402 |
"ariellee/SuperPlatty-30B": ModelType.SFT,
|
403 |
"danielhanchen/open_llama_3b_600bt_preview": ModelType.SFT,
|
404 |
"cerebras/Cerebras-GPT-256M": ModelType.PT,
|
|
|
428 |
"upstage/llama-30b-instruct-2048": ModelType.SFT,
|
429 |
"upstage/llama-30b-instruct": ModelType.SFT,
|
430 |
"WizardLM/WizardLM-13B-1.0": ModelType.SFT,
|
431 |
+
"WizardLM/WizardLM-13B-V1.1": ModelType.SFT,
|
432 |
"WizardLM/WizardLM-30B-V1.0": ModelType.SFT,
|
433 |
"WizardLM/WizardCoder-15B-V1.0": ModelType.SFT,
|
434 |
"gpt2": ModelType.PT,
|
|
|
467 |
"h2oai/h2ogpt-gm-oasst1-en-1024-12b": ModelType.SFT,
|
468 |
"h2oai/h2ogpt-gm-oasst1-multilang-1024-20b": ModelType.SFT,
|
469 |
"bofenghuang/vigogne-13b-instruct": ModelType.SFT,
|
470 |
+
"bofenghuang/vigogne-13b-chat": ModelType.SFT,
|
471 |
"Vmware/open-llama-7b-v2-open-instruct": ModelType.SFT,
|
472 |
"VMware/open-llama-0.7T-7B-open-instruct-v1.1": ModelType.SFT,
|
473 |
"ewof/koishi-instruct-3b": ModelType.SFT,
|
474 |
+
"gywy/llama2-13b-chinese-v1": ModelType.SFT,
|
475 |
+
"64bits/LexPodLM-13B": ModelType.SFT
|
476 |
}
|
477 |
|
478 |
|