List Models

GET

https://host.com/apis/models/v2/workspaces/:workspace/models

GET

/apis/models/v2/workspaces/:workspace/models

$ curl https://host.com/apis/models/v2/workspaces/workspace/models \
>      -H "Content-Type: application/json"

1 {
2   "data": [
3     {
4       "id": "a3f47b2e-9c4d-4f1a-8b2e-3d7f9a1c2b4e",
5       "name": "llama-3.1-8b",
6       "workspace": "research-team",
7       "created_at": "2024-01-15T09:30:00Z",
8       "updated_at": "2024-04-10T12:45:00Z",
9       "project": "nlp-optimization",
10       "description": "LLaMA 3.1 8B parameter model fine-tuned for chat applications.",
11       "spec": {
12         "checkpoint_model_name": "llama-3.1-8b-v1.0",
13         "family": "llama",
14         "num_layers": 32,
15         "hidden_size": 5120,
16         "num_attention_heads": 40,
17         "num_kv_heads": 40,
18         "ffn_hidden_size": 13824,
19         "vocab_size": 32000,
20         "tied_embeddings": true,
21         "gated_mlp": false,
22         "base_num_parameters": 8000000000,
23         "precision": "float16",
24         "context_size": 4096,
25         "num_virtual_tokens": 20,
26         "is_chat": true,
27         "is_embedding_model": false,
28         "moe_config": {
29           "num_experts": 0,
30           "num_experts_per_tok": 0,
31           "num_expert_layers": 0,
32           "expert_ffn_size": 0,
33           "num_shared_experts": 0
34         },
35         "mamba_config": {
36           "is_hybrid": false,
37           "num_mamba_layers": 0,
38           "num_attention_layers": 0,
39           "num_mlp_layers": 0,
40           "state_size": 16,
41           "conv_kernel": 4
42         },
43         "sliding_window_config": {
44           "window_size": 512
45         },
46         "linear_layers": [
47           {
48             "name": "model.layers.0.self_attn.q_proj",
49             "in_features": 5120,
50             "out_features": 5120
51           },
52           {
53             "name": "model.layers.0.mlp.fc1",
54             "in_features": 5120,
55             "out_features": 13824
56           }
57         ],
58         "chat_template": "You are a helpful assistant. {{icl_few_shot_examples}}",
59         "tool_call_config": {
60           "tool_call_parser": "openai",
61           "tool_call_plugin": "research-team/tool-call-plugin-v1",
62           "auto_tool_choice": true
63         },
64         "minimum_gpus_all_weights": 4,
65         "minimum_gpus_lora": 1
66       },
67       "finetuning_type": "lora_merged",
68       "fileset": "research-team/llama-3.1-8b-fileset",
69       "trust_remote_code": false,
70       "base_model": "llama-3.0-8b",
71       "api_endpoint": {
72         "url": "https://api.nemo-platform.com/v1/models/llama-3.1-8b/infer",
73         "model_id": "llama-3.1-8b",
74         "api_key": "sk-abc123def456ghi789jkl",
75         "format": "openai"
76       },
77       "backend_format": "OPENAI_CHAT",
78       "adapters": [
79         {
80           "name": "lora-adapter-v1",
81           "workspace": "research-team",
82           "fileset": "research-team/lora-adapter-legal-v1",
83           "finetuning_type": "lora_merged",
84           "description": "LoRA adapter for domain-specific tuning on legal texts.",
85           "enabled": true,
86           "lora_config": {
87             "rank": 8,
88             "alpha": 16
89           },
90           "model": "research-team/llama-3.1-8b",
91           "created_at": "2024-02-20T11:00:00Z",
92           "updated_at": "2024-03-05T15:30:00Z"
93         }
94       ],
95       "prompt": {
96         "system_prompt": "You are a helpful assistant specialized in legal documents.",
97         "icl_few_shot_examples": "Q: What is the statute of limitations for contract disputes?\nA: Typically 6 years in most jurisdictions.",
98         "inference_params": {
99           "model": "llama-3.1-8b",
100           "temperature": 0.7,
101           "max_tokens": 512,
102           "max_completion_tokens": 256,
103           "top_p": 0.9,
104           "stop": [
105             "\n\n"
106           ]
107         },
108         "system_prompt_template": "System: {{system_prompt}}\nExamples: {{icl_few_shot_examples}}"
109       },
110       "custom_fields": {
111         "release_stage": "beta",
112         "supported_languages": [
113           "en",
114           "es",
115           "fr"
116         ]
117       },
118       "ownership": {
119         "owner": "research-team",
120         "contact_email": "nlp-team@nemo-platform.com"
121       },
122       "model_providers": [
123         "nemo-inference/llama-3.1-8b-provider"
124       ]
125     }
126   ],
127   "pagination": {
128     "page": 1,
129     "page_size": 10,
130     "current_page_size": 1,
131     "total_pages": 1,
132     "total_results": 1
133   },
134   "sort": "created_at",
135   "filter": {}
136 }

List Models endpoint with filtering, pagination, and sorting.

Supports filter parameters for various criteria (including peft, custom fields), pagination (page, page_size), sorting, and workspace filtering via query parameter.

Path parameters

workspacestringRequired

Query parameters

pageintegerOptionalDefaults to 1

Page number.

page_sizeintegerOptionalDefaults to 100

Page size.

sortenumOptionalDefaults to created_at

The field to sort by. To sort in decreasing order, use - in front of the field name.

verbosebooleanOptionalDefaults to false

Whether to include full spec details

filterobjectOptional

Filter models by name, project, workspace, base_model, adapters, finetuning_type, prompt, lora_enabled, description, created_at, and updated_at.

Response

Return a list of models

datalist of objects

paginationobject

Pagination information.

sortstring

The field on which the results are sorted.

filtermap from strings to any

Filtering information.

Errors

422

Unprocessable Entity Error