Spaces:
Running
on
CPU Upgrade
Running
on
CPU Upgrade
eduagarcia
commited on
Commit
•
4a005f5
1
Parent(s):
33e7caf
update README
Browse files- README.md +34 -0
- model_list.txt +34 -0
- update_models_in_readme.py +1 -0
README.md
CHANGED
@@ -107,6 +107,7 @@ models:
|
|
107 |
- EleutherAI/pythia-6.9b-deduped
|
108 |
- EleutherAI/pythia-70m
|
109 |
- EleutherAI/pythia-70m-deduped
|
|
|
110 |
- FuseAI/FuseChat-7B-VaRM
|
111 |
- FuseAI/OpenChat-3.5-7B-Solar
|
112 |
- GeneZC/MiniChat-1.5-3B
|
@@ -148,17 +149,22 @@ models:
|
|
148 |
- Kukedlc/NeuralSynthesis-7B-v0.1
|
149 |
- Kukedlc/NeuralSynthesis-7B-v0.3
|
150 |
- Kukedlc/NeuralSynthesis-7b-v0.4-slerp
|
|
|
151 |
- LiteAI/Hare-1.1B-Chat
|
152 |
- LiteAI/Hare-1.1B-base
|
153 |
- M4-ai/tau-0.5B
|
154 |
- M4-ai/tau-0.5B-instruct-DPOP
|
155 |
- M4-ai/tau-1.8B
|
156 |
- MTSAIR/multi_verse_model
|
|
|
157 |
- Magpie-Align/Llama-3-8B-Magpie-Align-v0.3
|
|
|
158 |
- MagusCorp/legislinho
|
159 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.1
|
160 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.2
|
|
|
161 |
- MaziyarPanahi/Llama-3-8B-Instruct-v0.8
|
|
|
162 |
- MaziyarPanahi/Mistral-7B-Instruct-Aya-101
|
163 |
- MaziyarPanahi/Mistral-7B-Instruct-v0.3
|
164 |
- MaziyarPanahi/Mistral-7B-v0.3
|
@@ -168,6 +174,7 @@ models:
|
|
168 |
- NLPark/AnFeng_v3.1-Avocet
|
169 |
- NLPark/AnFeng_v3_Avocet
|
170 |
- NOVA-vision-language/GlorIA-1.3B
|
|
|
171 |
- Nexusflow/Starling-LM-7B-beta
|
172 |
- Nos-PT/Carvalho_pt-gl-1.3B
|
173 |
- NotAiLOL/Yi-1.5-dolphin-9B
|
@@ -208,6 +215,7 @@ models:
|
|
208 |
- Qwen/Qwen1.5-0.5B-Chat
|
209 |
- Qwen/Qwen1.5-1.8B
|
210 |
- Qwen/Qwen1.5-1.8B-Chat
|
|
|
211 |
- Qwen/Qwen1.5-110B-Chat
|
212 |
- Qwen/Qwen1.5-14B
|
213 |
- Qwen/Qwen1.5-14B-Chat
|
@@ -223,6 +231,7 @@ models:
|
|
223 |
- Qwen/Qwen1.5-MoE-A2.7B-Chat
|
224 |
- Qwen/Qwen2-0.5B
|
225 |
- Qwen/Qwen2-0.5B-Instruct
|
|
|
226 |
- Qwen/Qwen2-72B
|
227 |
- Qwen/Qwen2-72B-Instruct
|
228 |
- Qwen/Qwen2-7B
|
@@ -270,9 +279,12 @@ models:
|
|
270 |
- UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3
|
271 |
- Unbabel/TowerBase-7B-v0.1
|
272 |
- VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
|
|
|
273 |
- VAGOsolutions/SauerkrautLM-Gemma-7b
|
274 |
- VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
|
275 |
- VAGOsolutions/SauerkrautLM-Qwen-32b
|
|
|
|
|
276 |
- Walmart-the-bag/Misted-v2-7B
|
277 |
- Walmart-the-bag/Quintellect-10.7B
|
278 |
- Walmart-the-bag/WordWoven-2x7B
|
@@ -331,6 +343,8 @@ models:
|
|
331 |
- alvarobartt/mistral-orpo-mix
|
332 |
- alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt
|
333 |
- amazingvince/Not-WizardLM-2-7B
|
|
|
|
|
334 |
- argilla/CapybaraHermes-2.5-Mistral-7B
|
335 |
- argilla/notus-7b-v1
|
336 |
- argilla/notux-8x7b-v1
|
@@ -369,6 +383,7 @@ models:
|
|
369 |
- cnmoro/Mistral-7B-Portuguese
|
370 |
- cognitivecomputations/WestLake-7B-v2-laser
|
371 |
- cognitivecomputations/WizardLM-13B-Uncensored
|
|
|
372 |
- cognitivecomputations/WizardLM-7B-Uncensored
|
373 |
- cognitivecomputations/dolphin-2.9-llama3-8b
|
374 |
- cognitivecomputations/dolphin-2.9.1-llama-3-70b
|
@@ -381,6 +396,7 @@ models:
|
|
381 |
- cognitivecomputations/dolphin-2.9.3-llama-3-8b
|
382 |
- cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
|
383 |
- cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
|
|
|
384 |
- cognitivecomputations/openchat-3.5-0106-laser
|
385 |
- cognitivess/bella-1-8b
|
386 |
- cosmicvalor/mistral-orthogonalized
|
@@ -435,12 +451,17 @@ models:
|
|
435 |
- fblgit/UNA-SimpleSmaug-34b-v1beta
|
436 |
- fernandosola/bluearara-7B
|
437 |
- fernandosola/bluearara-7B-instruct
|
|
|
|
|
438 |
- freewheelin/free-solar-evo-v0.11
|
|
|
439 |
- ghost-x/ghost-8b-beta
|
440 |
- google/gemma-1.1-2b-it
|
441 |
- google/gemma-1.1-7b-it
|
442 |
- google/gemma-2-27b
|
443 |
- google/gemma-2-27b-it
|
|
|
|
|
444 |
- google/gemma-2-9b
|
445 |
- google/gemma-2-9b-it
|
446 |
- google/gemma-2b
|
@@ -453,6 +474,7 @@ models:
|
|
453 |
- google/recurrentgemma-2b-it
|
454 |
- gpt2
|
455 |
- gradientai/Llama-3-8B-Instruct-262k
|
|
|
456 |
- h2oai/h2o-danube-1.8b-base
|
457 |
- h2oai/h2o-danube-1.8b-chat
|
458 |
- h2oai/h2o-danube-1.8b-sft
|
@@ -490,6 +512,10 @@ models:
|
|
490 |
- internlm/internlm2-chat-7b
|
491 |
- internlm/internlm2-chat-7b-sft
|
492 |
- internlm/internlm2-wqx-20b
|
|
|
|
|
|
|
|
|
493 |
- internlm/internlm2_5-7b
|
494 |
- internlm/internlm2_5-7b-chat
|
495 |
- internlm/internlm2_5-7b-chat-1m
|
@@ -540,6 +566,7 @@ models:
|
|
540 |
- meta-llama/Meta-Llama-3-70B-Instruct
|
541 |
- meta-llama/Meta-Llama-3-8B
|
542 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
|
|
543 |
- meta-llama/Meta-Llama-3.1-70B
|
544 |
- meta-llama/Meta-Llama-3.1-70B-Instruct
|
545 |
- meta-llama/Meta-Llama-3.1-8B
|
@@ -578,6 +605,7 @@ models:
|
|
578 |
- mlabonne/NeuralDaredevil-8B-abliterated
|
579 |
- mlabonne/NeuralMonarch-7B
|
580 |
- monilouise/opt125M_portuguese
|
|
|
581 |
- mosaicml/mpt-7b
|
582 |
- mosaicml/mpt-7b-8k
|
583 |
- natong19/Qwen2-7B-Instruct-abliterated
|
@@ -594,6 +622,7 @@ models:
|
|
594 |
- nicolasdec/CabraQwen7b
|
595 |
- nicolasdec/Cabramistral7b
|
596 |
- nicolasdec/cabra13b
|
|
|
597 |
- nvidia/Nemotron-4-340B-Instruct
|
598 |
- openai-community/gpt2-large
|
599 |
- openai-community/gpt2-medium
|
@@ -613,7 +642,9 @@ models:
|
|
613 |
- pierreguillou/gpt2-small-portuguese
|
614 |
- premai-io/prem-1B-chat
|
615 |
- princeton-nlp/Llama-3-Instruct-8B-SimPO
|
|
|
616 |
- princeton-nlp/Mistral-7B-Base-SFT-SimPO
|
|
|
617 |
- projecte-aina/FLOR-1.3B
|
618 |
- projecte-aina/FLOR-6.3B
|
619 |
- projecte-aina/FLOR-760M
|
@@ -707,6 +738,8 @@ models:
|
|
707 |
- togethercomputer/RedPajama-INCITE-Base-3B-v1
|
708 |
- unicamp-dl/ptt5-base-portuguese-vocab
|
709 |
- unicamp-dl/ptt5-small-portuguese-vocab
|
|
|
|
|
710 |
- unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
711 |
- unsloth/gemma-2b-bnb-4bit
|
712 |
- unsloth/gemma-7b-bnb-4bit
|
@@ -726,6 +759,7 @@ models:
|
|
726 |
- vicgalle/CarbonBeagle-11B-truthy
|
727 |
- vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
|
728 |
- vicgalle/Configurable-Llama-3-8B-v0.3
|
|
|
729 |
- vicgalle/Configurable-Mistral-7B
|
730 |
- vicgalle/Configurable-Yi-1.5-9B-Chat
|
731 |
- vicgalle/ConfigurableBeagle-11B
|
|
|
107 |
- EleutherAI/pythia-6.9b-deduped
|
108 |
- EleutherAI/pythia-70m
|
109 |
- EleutherAI/pythia-70m-deduped
|
110 |
+
- Eurdem/Defne-llama3.1-8B
|
111 |
- FuseAI/FuseChat-7B-VaRM
|
112 |
- FuseAI/OpenChat-3.5-7B-Solar
|
113 |
- GeneZC/MiniChat-1.5-3B
|
|
|
149 |
- Kukedlc/NeuralSynthesis-7B-v0.1
|
150 |
- Kukedlc/NeuralSynthesis-7B-v0.3
|
151 |
- Kukedlc/NeuralSynthesis-7b-v0.4-slerp
|
152 |
+
- LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
|
153 |
- LiteAI/Hare-1.1B-Chat
|
154 |
- LiteAI/Hare-1.1B-base
|
155 |
- M4-ai/tau-0.5B
|
156 |
- M4-ai/tau-0.5B-instruct-DPOP
|
157 |
- M4-ai/tau-1.8B
|
158 |
- MTSAIR/multi_verse_model
|
159 |
+
- Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3
|
160 |
- Magpie-Align/Llama-3-8B-Magpie-Align-v0.3
|
161 |
+
- Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1
|
162 |
- MagusCorp/legislinho
|
163 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.1
|
164 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.2
|
165 |
+
- MaziyarPanahi/Llama-3-8B-Instruct-v0.10
|
166 |
- MaziyarPanahi/Llama-3-8B-Instruct-v0.8
|
167 |
+
- MaziyarPanahi/Llama-3-8B-Instruct-v0.9
|
168 |
- MaziyarPanahi/Mistral-7B-Instruct-Aya-101
|
169 |
- MaziyarPanahi/Mistral-7B-Instruct-v0.3
|
170 |
- MaziyarPanahi/Mistral-7B-v0.3
|
|
|
174 |
- NLPark/AnFeng_v3.1-Avocet
|
175 |
- NLPark/AnFeng_v3_Avocet
|
176 |
- NOVA-vision-language/GlorIA-1.3B
|
177 |
+
- NTQAI/Nxcode-CQ-7B-orpo
|
178 |
- Nexusflow/Starling-LM-7B-beta
|
179 |
- Nos-PT/Carvalho_pt-gl-1.3B
|
180 |
- NotAiLOL/Yi-1.5-dolphin-9B
|
|
|
215 |
- Qwen/Qwen1.5-0.5B-Chat
|
216 |
- Qwen/Qwen1.5-1.8B
|
217 |
- Qwen/Qwen1.5-1.8B-Chat
|
218 |
+
- Qwen/Qwen1.5-110B
|
219 |
- Qwen/Qwen1.5-110B-Chat
|
220 |
- Qwen/Qwen1.5-14B
|
221 |
- Qwen/Qwen1.5-14B-Chat
|
|
|
231 |
- Qwen/Qwen1.5-MoE-A2.7B-Chat
|
232 |
- Qwen/Qwen2-0.5B
|
233 |
- Qwen/Qwen2-0.5B-Instruct
|
234 |
+
- Qwen/Qwen2-57B-A14B
|
235 |
- Qwen/Qwen2-72B
|
236 |
- Qwen/Qwen2-72B-Instruct
|
237 |
- Qwen/Qwen2-7B
|
|
|
279 |
- UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3
|
280 |
- Unbabel/TowerBase-7B-v0.1
|
281 |
- VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
|
282 |
+
- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
|
283 |
- VAGOsolutions/SauerkrautLM-Gemma-7b
|
284 |
- VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
|
285 |
- VAGOsolutions/SauerkrautLM-Qwen-32b
|
286 |
+
- ValiantLabs/Llama3.1-8B-Fireplace2
|
287 |
+
- ValiantLabs/Llama3.1-8B-ShiningValiant2
|
288 |
- Walmart-the-bag/Misted-v2-7B
|
289 |
- Walmart-the-bag/Quintellect-10.7B
|
290 |
- Walmart-the-bag/WordWoven-2x7B
|
|
|
343 |
- alvarobartt/mistral-orpo-mix
|
344 |
- alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt
|
345 |
- amazingvince/Not-WizardLM-2-7B
|
346 |
+
- arcee-ai/Arcee-Scribe
|
347 |
+
- arcee-ai/Arcee-Spark
|
348 |
- argilla/CapybaraHermes-2.5-Mistral-7B
|
349 |
- argilla/notus-7b-v1
|
350 |
- argilla/notux-8x7b-v1
|
|
|
383 |
- cnmoro/Mistral-7B-Portuguese
|
384 |
- cognitivecomputations/WestLake-7B-v2-laser
|
385 |
- cognitivecomputations/WizardLM-13B-Uncensored
|
386 |
+
- cognitivecomputations/WizardLM-30B-Uncensored
|
387 |
- cognitivecomputations/WizardLM-7B-Uncensored
|
388 |
- cognitivecomputations/dolphin-2.9-llama3-8b
|
389 |
- cognitivecomputations/dolphin-2.9.1-llama-3-70b
|
|
|
396 |
- cognitivecomputations/dolphin-2.9.3-llama-3-8b
|
397 |
- cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
|
398 |
- cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
|
399 |
+
- cognitivecomputations/laserxtral
|
400 |
- cognitivecomputations/openchat-3.5-0106-laser
|
401 |
- cognitivess/bella-1-8b
|
402 |
- cosmicvalor/mistral-orthogonalized
|
|
|
451 |
- fblgit/UNA-SimpleSmaug-34b-v1beta
|
452 |
- fernandosola/bluearara-7B
|
453 |
- fernandosola/bluearara-7B-instruct
|
454 |
+
- freewheelin/free-llama3-dpo-v0.2
|
455 |
+
- freewheelin/free-solar-evo-v0.1
|
456 |
- freewheelin/free-solar-evo-v0.11
|
457 |
+
- freewheelin/free-solar-evo-v0.13
|
458 |
- ghost-x/ghost-8b-beta
|
459 |
- google/gemma-1.1-2b-it
|
460 |
- google/gemma-1.1-7b-it
|
461 |
- google/gemma-2-27b
|
462 |
- google/gemma-2-27b-it
|
463 |
+
- google/gemma-2-2b
|
464 |
+
- google/gemma-2-2b-it
|
465 |
- google/gemma-2-9b
|
466 |
- google/gemma-2-9b-it
|
467 |
- google/gemma-2b
|
|
|
474 |
- google/recurrentgemma-2b-it
|
475 |
- gpt2
|
476 |
- gradientai/Llama-3-8B-Instruct-262k
|
477 |
+
- grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
|
478 |
- h2oai/h2o-danube-1.8b-base
|
479 |
- h2oai/h2o-danube-1.8b-chat
|
480 |
- h2oai/h2o-danube-1.8b-sft
|
|
|
512 |
- internlm/internlm2-chat-7b
|
513 |
- internlm/internlm2-chat-7b-sft
|
514 |
- internlm/internlm2-wqx-20b
|
515 |
+
- internlm/internlm2_5-1_8b
|
516 |
+
- internlm/internlm2_5-1_8b-chat
|
517 |
+
- internlm/internlm2_5-20b
|
518 |
+
- internlm/internlm2_5-20b-chat
|
519 |
- internlm/internlm2_5-7b
|
520 |
- internlm/internlm2_5-7b-chat
|
521 |
- internlm/internlm2_5-7b-chat-1m
|
|
|
566 |
- meta-llama/Meta-Llama-3-70B-Instruct
|
567 |
- meta-llama/Meta-Llama-3-8B
|
568 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
569 |
+
- meta-llama/Meta-Llama-3.1-405B-Instruct
|
570 |
- meta-llama/Meta-Llama-3.1-70B
|
571 |
- meta-llama/Meta-Llama-3.1-70B-Instruct
|
572 |
- meta-llama/Meta-Llama-3.1-8B
|
|
|
605 |
- mlabonne/NeuralDaredevil-8B-abliterated
|
606 |
- mlabonne/NeuralMonarch-7B
|
607 |
- monilouise/opt125M_portuguese
|
608 |
+
- mosaicml/mpt-30b
|
609 |
- mosaicml/mpt-7b
|
610 |
- mosaicml/mpt-7b-8k
|
611 |
- natong19/Qwen2-7B-Instruct-abliterated
|
|
|
622 |
- nicolasdec/CabraQwen7b
|
623 |
- nicolasdec/Cabramistral7b
|
624 |
- nicolasdec/cabra13b
|
625 |
+
- nisten/Biggie-SmoLlm-0.15B-Base
|
626 |
- nvidia/Nemotron-4-340B-Instruct
|
627 |
- openai-community/gpt2-large
|
628 |
- openai-community/gpt2-medium
|
|
|
642 |
- pierreguillou/gpt2-small-portuguese
|
643 |
- premai-io/prem-1B-chat
|
644 |
- princeton-nlp/Llama-3-Instruct-8B-SimPO
|
645 |
+
- princeton-nlp/Llama-3-Instruct-8B-SimPO-v0.2
|
646 |
- princeton-nlp/Mistral-7B-Base-SFT-SimPO
|
647 |
+
- princeton-nlp/gemma-2-9b-it-SimPO
|
648 |
- projecte-aina/FLOR-1.3B
|
649 |
- projecte-aina/FLOR-6.3B
|
650 |
- projecte-aina/FLOR-760M
|
|
|
738 |
- togethercomputer/RedPajama-INCITE-Base-3B-v1
|
739 |
- unicamp-dl/ptt5-base-portuguese-vocab
|
740 |
- unicamp-dl/ptt5-small-portuguese-vocab
|
741 |
+
- unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit
|
742 |
+
- unsloth/Meta-Llama-3.1-70B-bnb-4bit
|
743 |
- unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
744 |
- unsloth/gemma-2b-bnb-4bit
|
745 |
- unsloth/gemma-7b-bnb-4bit
|
|
|
759 |
- vicgalle/CarbonBeagle-11B-truthy
|
760 |
- vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
|
761 |
- vicgalle/Configurable-Llama-3-8B-v0.3
|
762 |
+
- vicgalle/Configurable-Llama-3.1-8B-Instruct
|
763 |
- vicgalle/Configurable-Mistral-7B
|
764 |
- vicgalle/Configurable-Yi-1.5-9B-Chat
|
765 |
- vicgalle/ConfigurableBeagle-11B
|
model_list.txt
CHANGED
@@ -78,6 +78,7 @@
|
|
78 |
- EleutherAI/pythia-6.9b-deduped
|
79 |
- EleutherAI/pythia-70m
|
80 |
- EleutherAI/pythia-70m-deduped
|
|
|
81 |
- FuseAI/FuseChat-7B-VaRM
|
82 |
- FuseAI/OpenChat-3.5-7B-Solar
|
83 |
- GeneZC/MiniChat-1.5-3B
|
@@ -119,17 +120,22 @@
|
|
119 |
- Kukedlc/NeuralSynthesis-7B-v0.1
|
120 |
- Kukedlc/NeuralSynthesis-7B-v0.3
|
121 |
- Kukedlc/NeuralSynthesis-7b-v0.4-slerp
|
|
|
122 |
- LiteAI/Hare-1.1B-Chat
|
123 |
- LiteAI/Hare-1.1B-base
|
124 |
- M4-ai/tau-0.5B
|
125 |
- M4-ai/tau-0.5B-instruct-DPOP
|
126 |
- M4-ai/tau-1.8B
|
127 |
- MTSAIR/multi_verse_model
|
|
|
128 |
- Magpie-Align/Llama-3-8B-Magpie-Align-v0.3
|
|
|
129 |
- MagusCorp/legislinho
|
130 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.1
|
131 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.2
|
|
|
132 |
- MaziyarPanahi/Llama-3-8B-Instruct-v0.8
|
|
|
133 |
- MaziyarPanahi/Mistral-7B-Instruct-Aya-101
|
134 |
- MaziyarPanahi/Mistral-7B-Instruct-v0.3
|
135 |
- MaziyarPanahi/Mistral-7B-v0.3
|
@@ -139,6 +145,7 @@
|
|
139 |
- NLPark/AnFeng_v3.1-Avocet
|
140 |
- NLPark/AnFeng_v3_Avocet
|
141 |
- NOVA-vision-language/GlorIA-1.3B
|
|
|
142 |
- Nexusflow/Starling-LM-7B-beta
|
143 |
- Nos-PT/Carvalho_pt-gl-1.3B
|
144 |
- NotAiLOL/Yi-1.5-dolphin-9B
|
@@ -179,6 +186,7 @@
|
|
179 |
- Qwen/Qwen1.5-0.5B-Chat
|
180 |
- Qwen/Qwen1.5-1.8B
|
181 |
- Qwen/Qwen1.5-1.8B-Chat
|
|
|
182 |
- Qwen/Qwen1.5-110B-Chat
|
183 |
- Qwen/Qwen1.5-14B
|
184 |
- Qwen/Qwen1.5-14B-Chat
|
@@ -194,6 +202,7 @@
|
|
194 |
- Qwen/Qwen1.5-MoE-A2.7B-Chat
|
195 |
- Qwen/Qwen2-0.5B
|
196 |
- Qwen/Qwen2-0.5B-Instruct
|
|
|
197 |
- Qwen/Qwen2-72B
|
198 |
- Qwen/Qwen2-72B-Instruct
|
199 |
- Qwen/Qwen2-7B
|
@@ -241,9 +250,12 @@
|
|
241 |
- UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3
|
242 |
- Unbabel/TowerBase-7B-v0.1
|
243 |
- VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
|
|
|
244 |
- VAGOsolutions/SauerkrautLM-Gemma-7b
|
245 |
- VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
|
246 |
- VAGOsolutions/SauerkrautLM-Qwen-32b
|
|
|
|
|
247 |
- Walmart-the-bag/Misted-v2-7B
|
248 |
- Walmart-the-bag/Quintellect-10.7B
|
249 |
- Walmart-the-bag/WordWoven-2x7B
|
@@ -302,6 +314,8 @@
|
|
302 |
- alvarobartt/mistral-orpo-mix
|
303 |
- alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt
|
304 |
- amazingvince/Not-WizardLM-2-7B
|
|
|
|
|
305 |
- argilla/CapybaraHermes-2.5-Mistral-7B
|
306 |
- argilla/notus-7b-v1
|
307 |
- argilla/notux-8x7b-v1
|
@@ -340,6 +354,7 @@
|
|
340 |
- cnmoro/Mistral-7B-Portuguese
|
341 |
- cognitivecomputations/WestLake-7B-v2-laser
|
342 |
- cognitivecomputations/WizardLM-13B-Uncensored
|
|
|
343 |
- cognitivecomputations/WizardLM-7B-Uncensored
|
344 |
- cognitivecomputations/dolphin-2.9-llama3-8b
|
345 |
- cognitivecomputations/dolphin-2.9.1-llama-3-70b
|
@@ -352,6 +367,7 @@
|
|
352 |
- cognitivecomputations/dolphin-2.9.3-llama-3-8b
|
353 |
- cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
|
354 |
- cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
|
|
|
355 |
- cognitivecomputations/openchat-3.5-0106-laser
|
356 |
- cognitivess/bella-1-8b
|
357 |
- cosmicvalor/mistral-orthogonalized
|
@@ -406,12 +422,17 @@
|
|
406 |
- fblgit/UNA-SimpleSmaug-34b-v1beta
|
407 |
- fernandosola/bluearara-7B
|
408 |
- fernandosola/bluearara-7B-instruct
|
|
|
|
|
409 |
- freewheelin/free-solar-evo-v0.11
|
|
|
410 |
- ghost-x/ghost-8b-beta
|
411 |
- google/gemma-1.1-2b-it
|
412 |
- google/gemma-1.1-7b-it
|
413 |
- google/gemma-2-27b
|
414 |
- google/gemma-2-27b-it
|
|
|
|
|
415 |
- google/gemma-2-9b
|
416 |
- google/gemma-2-9b-it
|
417 |
- google/gemma-2b
|
@@ -424,6 +445,7 @@
|
|
424 |
- google/recurrentgemma-2b-it
|
425 |
- gpt2
|
426 |
- gradientai/Llama-3-8B-Instruct-262k
|
|
|
427 |
- h2oai/h2o-danube-1.8b-base
|
428 |
- h2oai/h2o-danube-1.8b-chat
|
429 |
- h2oai/h2o-danube-1.8b-sft
|
@@ -461,6 +483,10 @@
|
|
461 |
- internlm/internlm2-chat-7b
|
462 |
- internlm/internlm2-chat-7b-sft
|
463 |
- internlm/internlm2-wqx-20b
|
|
|
|
|
|
|
|
|
464 |
- internlm/internlm2_5-7b
|
465 |
- internlm/internlm2_5-7b-chat
|
466 |
- internlm/internlm2_5-7b-chat-1m
|
@@ -511,6 +537,7 @@
|
|
511 |
- meta-llama/Meta-Llama-3-70B-Instruct
|
512 |
- meta-llama/Meta-Llama-3-8B
|
513 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
|
|
514 |
- meta-llama/Meta-Llama-3.1-70B
|
515 |
- meta-llama/Meta-Llama-3.1-70B-Instruct
|
516 |
- meta-llama/Meta-Llama-3.1-8B
|
@@ -549,6 +576,7 @@
|
|
549 |
- mlabonne/NeuralDaredevil-8B-abliterated
|
550 |
- mlabonne/NeuralMonarch-7B
|
551 |
- monilouise/opt125M_portuguese
|
|
|
552 |
- mosaicml/mpt-7b
|
553 |
- mosaicml/mpt-7b-8k
|
554 |
- natong19/Qwen2-7B-Instruct-abliterated
|
@@ -565,6 +593,7 @@
|
|
565 |
- nicolasdec/CabraQwen7b
|
566 |
- nicolasdec/Cabramistral7b
|
567 |
- nicolasdec/cabra13b
|
|
|
568 |
- nvidia/Nemotron-4-340B-Instruct
|
569 |
- openai-community/gpt2-large
|
570 |
- openai-community/gpt2-medium
|
@@ -584,7 +613,9 @@
|
|
584 |
- pierreguillou/gpt2-small-portuguese
|
585 |
- premai-io/prem-1B-chat
|
586 |
- princeton-nlp/Llama-3-Instruct-8B-SimPO
|
|
|
587 |
- princeton-nlp/Mistral-7B-Base-SFT-SimPO
|
|
|
588 |
- projecte-aina/FLOR-1.3B
|
589 |
- projecte-aina/FLOR-6.3B
|
590 |
- projecte-aina/FLOR-760M
|
@@ -678,6 +709,8 @@
|
|
678 |
- togethercomputer/RedPajama-INCITE-Base-3B-v1
|
679 |
- unicamp-dl/ptt5-base-portuguese-vocab
|
680 |
- unicamp-dl/ptt5-small-portuguese-vocab
|
|
|
|
|
681 |
- unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
682 |
- unsloth/gemma-2b-bnb-4bit
|
683 |
- unsloth/gemma-7b-bnb-4bit
|
@@ -697,6 +730,7 @@
|
|
697 |
- vicgalle/CarbonBeagle-11B-truthy
|
698 |
- vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
|
699 |
- vicgalle/Configurable-Llama-3-8B-v0.3
|
|
|
700 |
- vicgalle/Configurable-Mistral-7B
|
701 |
- vicgalle/Configurable-Yi-1.5-9B-Chat
|
702 |
- vicgalle/ConfigurableBeagle-11B
|
|
|
78 |
- EleutherAI/pythia-6.9b-deduped
|
79 |
- EleutherAI/pythia-70m
|
80 |
- EleutherAI/pythia-70m-deduped
|
81 |
+
- Eurdem/Defne-llama3.1-8B
|
82 |
- FuseAI/FuseChat-7B-VaRM
|
83 |
- FuseAI/OpenChat-3.5-7B-Solar
|
84 |
- GeneZC/MiniChat-1.5-3B
|
|
|
120 |
- Kukedlc/NeuralSynthesis-7B-v0.1
|
121 |
- Kukedlc/NeuralSynthesis-7B-v0.3
|
122 |
- Kukedlc/NeuralSynthesis-7b-v0.4-slerp
|
123 |
+
- LGAI-EXAONE/EXAONE-3.0-7.8B-Instruct
|
124 |
- LiteAI/Hare-1.1B-Chat
|
125 |
- LiteAI/Hare-1.1B-base
|
126 |
- M4-ai/tau-0.5B
|
127 |
- M4-ai/tau-0.5B-instruct-DPOP
|
128 |
- M4-ai/tau-1.8B
|
129 |
- MTSAIR/multi_verse_model
|
130 |
+
- Magpie-Align/Llama-3-8B-Magpie-Align-SFT-v0.3
|
131 |
- Magpie-Align/Llama-3-8B-Magpie-Align-v0.3
|
132 |
+
- Magpie-Align/Llama-3.1-8B-Magpie-Align-SFT-v0.1
|
133 |
- MagusCorp/legislinho
|
134 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.1
|
135 |
- MaziyarPanahi/Calme-4x7B-MoE-v0.2
|
136 |
+
- MaziyarPanahi/Llama-3-8B-Instruct-v0.10
|
137 |
- MaziyarPanahi/Llama-3-8B-Instruct-v0.8
|
138 |
+
- MaziyarPanahi/Llama-3-8B-Instruct-v0.9
|
139 |
- MaziyarPanahi/Mistral-7B-Instruct-Aya-101
|
140 |
- MaziyarPanahi/Mistral-7B-Instruct-v0.3
|
141 |
- MaziyarPanahi/Mistral-7B-v0.3
|
|
|
145 |
- NLPark/AnFeng_v3.1-Avocet
|
146 |
- NLPark/AnFeng_v3_Avocet
|
147 |
- NOVA-vision-language/GlorIA-1.3B
|
148 |
+
- NTQAI/Nxcode-CQ-7B-orpo
|
149 |
- Nexusflow/Starling-LM-7B-beta
|
150 |
- Nos-PT/Carvalho_pt-gl-1.3B
|
151 |
- NotAiLOL/Yi-1.5-dolphin-9B
|
|
|
186 |
- Qwen/Qwen1.5-0.5B-Chat
|
187 |
- Qwen/Qwen1.5-1.8B
|
188 |
- Qwen/Qwen1.5-1.8B-Chat
|
189 |
+
- Qwen/Qwen1.5-110B
|
190 |
- Qwen/Qwen1.5-110B-Chat
|
191 |
- Qwen/Qwen1.5-14B
|
192 |
- Qwen/Qwen1.5-14B-Chat
|
|
|
202 |
- Qwen/Qwen1.5-MoE-A2.7B-Chat
|
203 |
- Qwen/Qwen2-0.5B
|
204 |
- Qwen/Qwen2-0.5B-Instruct
|
205 |
+
- Qwen/Qwen2-57B-A14B
|
206 |
- Qwen/Qwen2-72B
|
207 |
- Qwen/Qwen2-72B-Instruct
|
208 |
- Qwen/Qwen2-7B
|
|
|
250 |
- UCLA-AGI/Mistral7B-PairRM-SPPO-Iter3
|
251 |
- Unbabel/TowerBase-7B-v0.1
|
252 |
- VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
|
253 |
+
- VAGOsolutions/Llama-3.1-SauerkrautLM-8b-Instruct
|
254 |
- VAGOsolutions/SauerkrautLM-Gemma-7b
|
255 |
- VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
|
256 |
- VAGOsolutions/SauerkrautLM-Qwen-32b
|
257 |
+
- ValiantLabs/Llama3.1-8B-Fireplace2
|
258 |
+
- ValiantLabs/Llama3.1-8B-ShiningValiant2
|
259 |
- Walmart-the-bag/Misted-v2-7B
|
260 |
- Walmart-the-bag/Quintellect-10.7B
|
261 |
- Walmart-the-bag/WordWoven-2x7B
|
|
|
314 |
- alvarobartt/mistral-orpo-mix
|
315 |
- alvarobartt/mistral-orpo-mix-b0.1-l2048-pl1792-lr5e-6-inverse-sqrt
|
316 |
- amazingvince/Not-WizardLM-2-7B
|
317 |
+
- arcee-ai/Arcee-Scribe
|
318 |
+
- arcee-ai/Arcee-Spark
|
319 |
- argilla/CapybaraHermes-2.5-Mistral-7B
|
320 |
- argilla/notus-7b-v1
|
321 |
- argilla/notux-8x7b-v1
|
|
|
354 |
- cnmoro/Mistral-7B-Portuguese
|
355 |
- cognitivecomputations/WestLake-7B-v2-laser
|
356 |
- cognitivecomputations/WizardLM-13B-Uncensored
|
357 |
+
- cognitivecomputations/WizardLM-30B-Uncensored
|
358 |
- cognitivecomputations/WizardLM-7B-Uncensored
|
359 |
- cognitivecomputations/dolphin-2.9-llama3-8b
|
360 |
- cognitivecomputations/dolphin-2.9.1-llama-3-70b
|
|
|
367 |
- cognitivecomputations/dolphin-2.9.3-llama-3-8b
|
368 |
- cognitivecomputations/dolphin-2.9.3-mistral-7B-32k
|
369 |
- cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b
|
370 |
+
- cognitivecomputations/laserxtral
|
371 |
- cognitivecomputations/openchat-3.5-0106-laser
|
372 |
- cognitivess/bella-1-8b
|
373 |
- cosmicvalor/mistral-orthogonalized
|
|
|
422 |
- fblgit/UNA-SimpleSmaug-34b-v1beta
|
423 |
- fernandosola/bluearara-7B
|
424 |
- fernandosola/bluearara-7B-instruct
|
425 |
+
- freewheelin/free-llama3-dpo-v0.2
|
426 |
+
- freewheelin/free-solar-evo-v0.1
|
427 |
- freewheelin/free-solar-evo-v0.11
|
428 |
+
- freewheelin/free-solar-evo-v0.13
|
429 |
- ghost-x/ghost-8b-beta
|
430 |
- google/gemma-1.1-2b-it
|
431 |
- google/gemma-1.1-7b-it
|
432 |
- google/gemma-2-27b
|
433 |
- google/gemma-2-27b-it
|
434 |
+
- google/gemma-2-2b
|
435 |
+
- google/gemma-2-2b-it
|
436 |
- google/gemma-2-9b
|
437 |
- google/gemma-2-9b-it
|
438 |
- google/gemma-2b
|
|
|
445 |
- google/recurrentgemma-2b-it
|
446 |
- gpt2
|
447 |
- gradientai/Llama-3-8B-Instruct-262k
|
448 |
+
- grimjim/Llama-3-Instruct-8B-SPPO-Iter3-SimPO-merge
|
449 |
- h2oai/h2o-danube-1.8b-base
|
450 |
- h2oai/h2o-danube-1.8b-chat
|
451 |
- h2oai/h2o-danube-1.8b-sft
|
|
|
483 |
- internlm/internlm2-chat-7b
|
484 |
- internlm/internlm2-chat-7b-sft
|
485 |
- internlm/internlm2-wqx-20b
|
486 |
+
- internlm/internlm2_5-1_8b
|
487 |
+
- internlm/internlm2_5-1_8b-chat
|
488 |
+
- internlm/internlm2_5-20b
|
489 |
+
- internlm/internlm2_5-20b-chat
|
490 |
- internlm/internlm2_5-7b
|
491 |
- internlm/internlm2_5-7b-chat
|
492 |
- internlm/internlm2_5-7b-chat-1m
|
|
|
537 |
- meta-llama/Meta-Llama-3-70B-Instruct
|
538 |
- meta-llama/Meta-Llama-3-8B
|
539 |
- meta-llama/Meta-Llama-3-8B-Instruct
|
540 |
+
- meta-llama/Meta-Llama-3.1-405B-Instruct
|
541 |
- meta-llama/Meta-Llama-3.1-70B
|
542 |
- meta-llama/Meta-Llama-3.1-70B-Instruct
|
543 |
- meta-llama/Meta-Llama-3.1-8B
|
|
|
576 |
- mlabonne/NeuralDaredevil-8B-abliterated
|
577 |
- mlabonne/NeuralMonarch-7B
|
578 |
- monilouise/opt125M_portuguese
|
579 |
+
- mosaicml/mpt-30b
|
580 |
- mosaicml/mpt-7b
|
581 |
- mosaicml/mpt-7b-8k
|
582 |
- natong19/Qwen2-7B-Instruct-abliterated
|
|
|
593 |
- nicolasdec/CabraQwen7b
|
594 |
- nicolasdec/Cabramistral7b
|
595 |
- nicolasdec/cabra13b
|
596 |
+
- nisten/Biggie-SmoLlm-0.15B-Base
|
597 |
- nvidia/Nemotron-4-340B-Instruct
|
598 |
- openai-community/gpt2-large
|
599 |
- openai-community/gpt2-medium
|
|
|
613 |
- pierreguillou/gpt2-small-portuguese
|
614 |
- premai-io/prem-1B-chat
|
615 |
- princeton-nlp/Llama-3-Instruct-8B-SimPO
|
616 |
+
- princeton-nlp/Llama-3-Instruct-8B-SimPO-v0.2
|
617 |
- princeton-nlp/Mistral-7B-Base-SFT-SimPO
|
618 |
+
- princeton-nlp/gemma-2-9b-it-SimPO
|
619 |
- projecte-aina/FLOR-1.3B
|
620 |
- projecte-aina/FLOR-6.3B
|
621 |
- projecte-aina/FLOR-760M
|
|
|
709 |
- togethercomputer/RedPajama-INCITE-Base-3B-v1
|
710 |
- unicamp-dl/ptt5-base-portuguese-vocab
|
711 |
- unicamp-dl/ptt5-small-portuguese-vocab
|
712 |
+
- unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit
|
713 |
+
- unsloth/Meta-Llama-3.1-70B-bnb-4bit
|
714 |
- unsloth/Phi-3-mini-4k-instruct-bnb-4bit
|
715 |
- unsloth/gemma-2b-bnb-4bit
|
716 |
- unsloth/gemma-7b-bnb-4bit
|
|
|
730 |
- vicgalle/CarbonBeagle-11B-truthy
|
731 |
- vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B
|
732 |
- vicgalle/Configurable-Llama-3-8B-v0.3
|
733 |
+
- vicgalle/Configurable-Llama-3.1-8B-Instruct
|
734 |
- vicgalle/Configurable-Mistral-7B
|
735 |
- vicgalle/Configurable-Yi-1.5-9B-Chat
|
736 |
- vicgalle/ConfigurableBeagle-11B
|
update_models_in_readme.py
CHANGED
@@ -19,6 +19,7 @@ import json
|
|
19 |
snapshot_download(repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30)
|
20 |
all_models = []
|
21 |
all_models.append('nvidia/Nemotron-4-340B-Instruct')
|
|
|
22 |
for filepath in glob.glob(os.path.join(EVAL_REQUESTS_PATH, '**/*.json'), recursive=True):
|
23 |
with open(filepath, 'r') as f:
|
24 |
model_data = json.load(f)
|
|
|
19 |
snapshot_download(repo_id=QUEUE_REPO, local_dir=EVAL_REQUESTS_PATH, repo_type="dataset", tqdm_class=None, etag_timeout=30)
|
20 |
all_models = []
|
21 |
all_models.append('nvidia/Nemotron-4-340B-Instruct')
|
22 |
+
all_models.append('meta-llama/Meta-Llama-3.1-405B-Instruct')
|
23 |
for filepath in glob.glob(os.path.join(EVAL_REQUESTS_PATH, '**/*.json'), recursive=True):
|
24 |
with open(filepath, 'r') as f:
|
25 |
model_data = json.load(f)
|