v1.11.0

版本发布时间: 2024-01-22 16:10:31

modelscope/modelscope最新发布版本:v1.18.1(2024-09-21 22:08:11)

New Models Recommended

No	Model Name & Link
0	Emu2-Gen
1	qanything_models
2	Emu2-Chat
3	Emu2
4	TinyLlama-1.1B-Chat-v1.0
5	notux-8x7b-v1
6	Machine_Mindset_en_ENFJ
7	Machine_Mindset_en_ENFP
8	Machine_Mindset_en_ENTJ
9	Machine_Mindset_en_ENTP
10	Machine_Mindset_en_ESFJ
11	Machine_Mindset_en_ESFP
12	Machine_Mindset_en_ESTJ
13	Machine_Mindset_en_ESTP
14	Machine_Mindset_en_INFJ
15	Machine_Mindset_en_INFP
16	Machine_Mindset_en_INTJ
17	Machine_Mindset_en_INTP
18	Machine_Mindset_en_ISFJ
19	Machine_Mindset_en_ISFP
20	Machine_Mindset_en_ISTJ
21	Machine_Mindset_en_ISTP
22	Machine_Mindset_zh_ENFJ
23	Machine_Mindset_zh_ENFP
24	Machine_Mindset_zh_ENTJ
25	Machine_Mindset_zh_ENTP
26	Machine_Mindset_zh_ESFJ
27	Machine_Mindset_zh_ESFP
28	Machine_Mindset_zh_ESTJ
29	Machine_Mindset_zh_ESTP
30	Machine_Mindset_zh_INFJ
31	Machine_Mindset_zh_INFP
32	Machine_Mindset_zh_INTJ
33	Machine_Mindset_zh_ISFJ
34	Machine_Mindset_zh_ISFP
35	Machine_Mindset_zh_ISTJ
36	Machine_Mindset_zh_ISTP
37	WavMark
38	speech_eres2net_large_200k_sv_zh-cn_16k-common
39	emotion2vec_base
30	QAnything
41	speech_fsmn_vad_zh-cn-8k-common-onnx
42	speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1-onnx
43	dolphin-2.6-mistral-7b
44	scepter_scedit
45	deepseek-moe-16b-base
46	deepseek-moe-16b-chat
47	phi-2
48	llava-internlm-7b
49	llava-v1.5-7b-xtuner
50	llava-v1.5-7b-xtuner-pretrain
51	llava-internlm-7b-pretrain
52	speech_ngram_lm_zh-cn-ai-wesp-fst-token8358
53	realisticVisionV51_v51VAE
54	THUDM_chatglm-6b
55	AnyDoor
56	cv_gaussian-splatting-recon_damo
57	AnimateDiff_ms
58	cv_omnidata_image-normal-estimation_normal
59	cv_rife_video-frame-interpolation
60	Qwen-7B-Chat-GGUF
61	stable-zero123
62	cv_adabins_image-depth-prediction_indoor
63	Qwen-14B-Chat-GGUF
64	wav2vec2-large-xlsr-53-english
65	speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
66	cv_resnet-transformer_local-feature-matching_outdoor-data
67	naturalspeech2_libritts
68	text_to_audio
69	valle_libritts
70	vits_ljspeech
71	hifigan_speech_bigdata
72	BigVGAN_singing_bigdata
73	singing_voice_conversion
74	Machine_Mindset_zh_INTP
75	bel_canto
76	music_genre
77	chest_falsetto
78	llava-v1.5-13b-xtuner
79	llava-v1.5-13b-xtuner-pretrain
80	Mistral-7B-Instruct-v0.2-GGUF
81	cv_transformer_image-matching_fast
82	cv_efficientsam-s_image-instance-segmentation_sa1b
83	Ziya-Visual-Lyrics-14B
84	dpo-sdxl-text2image-v1
85	mistral-ft-optimized-1218
86	IP-Adapter-FaceID
87	mask_refine
88	MindChat-Qwen-1_8B
89	AnyDoor_models
90	dolphin-2.5-mixtral-8x7b
91	SVHN-Recognition
92	cv_anytext_text_generation_editing
93	SOLAR-10.7B-Instruct-v1.0
94	insecta
95	pianos
96	kagentlms_baichuan2_13b_mat
97	kagentlms_qwen_7b_mat
98	cv_raft_dense-optical-flow_things
99	HEp2
100	cv_marigold_monocular-depth-estimation
101	OpenDalleV1.1
102	speech_sambert-hifigan_nsf_tts_emily_en-gb_24k
103	speech_sambert-hifigan_nsf_tts_eric_en-gb_24k
104	knowlm-13b-zhixi
105	RankingGPT-qwen-7b
106	hoyoGPT
107	RankingGPT-baichuan2-7b
108	RankingGPT-llama2-7b
109	RankingGPT-bloom-7b
110	RankingGPT-bloom-3b
111	RankingGPT-bloom-1b1
112	RankingGPT-bloom-560m
113	knowlm-13b-base-v1.0
114	knowlm-13b-ie
115	scepter_20240103-212734

Highlight

Add AnyDoor support (#688)
Add syncdreamer as a image-to-3d pipeline (#679)
Add audio codec and codec-based TTS model

Improvements

Update cuda to 12.1.0
Update transformers to 4.36.2
Update ckpt to general_v0.1 (#696)

BugFix

Fix embedding and inference device in faq question answering pipeline
Remove DOCKER_BUILDKIT=0 for cpu build issue
Fix mmcv-full issue

相关地址：原始地址下载(tar) 下载(zip)

查看：2024-01-22发行的版本