Get Model by Workspace and Name

GET

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

GET

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

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

1 {
2   "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
3   "name": "llama-3.1-8b",
4   "workspace": "research-team",
5   "created_at": "2024-01-15T09:30:00Z",
6   "updated_at": "2024-04-10T12:00:00Z",
7   "project": "urn:project:ai-models:llama",
8   "description": "LLaMA 3.1 8B parameter model optimized for chat and general purpose tasks.",
9   "spec": {
10     "checkpoint_model_name": "llama-3.1-8b-v1",
11     "family": "llama",
12     "num_layers": 32,
13     "hidden_size": 5120,
14     "num_attention_heads": 40,
15     "num_kv_heads": 40,
16     "ffn_hidden_size": 13824,
17     "vocab_size": 32000,
18     "tied_embeddings": true,
19     "gated_mlp": true,
20     "base_num_parameters": 8000000000,
21     "precision": "float16",
22     "context_size": 4096,
23     "num_virtual_tokens": 20,
24     "is_chat": true,
25     "is_embedding_model": false,
26     "moe_config": {
27       "num_experts": 16,
28       "num_experts_per_tok": 2,
29       "num_expert_layers": 4,
30       "expert_ffn_size": 16384,
31       "num_shared_experts": 0
32     },
33     "mamba_config": {
34       "is_hybrid": true,
35       "num_mamba_layers": 2,
36       "num_attention_layers": 1,
37       "num_mlp_layers": 1,
38       "state_size": 16,
39       "conv_kernel": 4
40     },
41     "sliding_window_config": {
42       "window_size": 512
43     },
44     "linear_layers": [
45       {
46         "name": "model.layers.0.self_attn.q_proj",
47         "in_features": 5120,
48         "out_features": 5120
49       }
50     ],
51     "chat_template": "You are a helpful assistant. {{icl_few_shot_examples}}",
52     "tool_call_config": {
53       "tool_call_parser": "openai",
54       "tool_call_plugin": "research-team/tool-call-plugin-v1",
55       "auto_tool_choice": true
56     },
57     "minimum_gpus_all_weights": 4,
58     "minimum_gpus_lora": 1
59   },
60   "finetuning_type": "lora_merged",
61   "fileset": "research-team/llama-3.1-8b-fileset",
62   "trust_remote_code": false,
63   "base_model": "research-team/llama-3.0-7b",
64   "api_endpoint": {
65     "url": "https://api.nemo.ai/v1/models/llama-3.1-8b/infer",
66     "model_id": "llama-3.1-8b-v1",
67     "api_key": "sk-abc123def456ghi789jkl",
68     "format": "openai"
69   },
70   "backend_format": "OPENAI_CHAT",
71   "adapters": [
72     {
73       "name": "lora-adapter-v1",
74       "workspace": "research-team",
75       "fileset": "research-team/lora-adapter-v1-fileset",
76       "finetuning_type": "lora_merged",
77       "description": "LoRA adapter fine-tuned on domain-specific data.",
78       "enabled": true,
79       "lora_config": {
80         "rank": 8,
81         "alpha": 32
82       },
83       "model": "research-team/llama-3.1-8b",
84       "created_at": "2024-02-20T10:00:00Z",
85       "updated_at": "2024-03-15T11:00:00Z"
86     }
87   ],
88   "prompt": {
89     "system_prompt": "You are a helpful assistant specialized in technical topics.",
90     "icl_few_shot_examples": "Q: What is the capital of France?\nA: Paris.\nQ: Who wrote 'Pride and Prejudice'?\nA: Jane Austen.",
91     "inference_params": {
92       "model": "llama-3.1-8b",
93       "temperature": 0.7,
94       "max_tokens": 512,
95       "max_completion_tokens": 256,
96       "top_p": 0.9,
97       "stop": [
98         "\n\n"
99       ]
100     },
101     "system_prompt_template": "System: {{system_prompt}}\nExamples:\n{{icl_few_shot_examples}}"
102   },
103   "custom_fields": {},
104   "ownership": {},
105   "model_providers": [
106     "providers/nemo-ai/llama-3.1-8b"
107   ]
108 }

Get Model by Workspace and Name. Returns the details of a specific model entity identified by its workspace and name.

Path parameters

workspacestringRequired

namestringRequired

Query parameters

verbosebooleanOptionalDefaults to false

Whether to include full spec details

Response

Return model details

idstring

Autogenerated id

namestringformat: "^[\w\-.]+$"<=255 characters

Name of the entity. Name/workspace combo must be unique across all entities. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

workspacestringformat: "^[\w\-.]+$"<=255 characters

The workspace of the entity. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

created_atdatetime

The timestamp of model entity creation

updated_atdatetime

The timestamp of the last model entity update

projectstring<=255 characters

The URN of the project associated with this model entity.

descriptionstring<=1000 characters

Optional description of the model.

specobject

Detailed specification for the model

finetuning_typeenum

Set for full weight finetuned models

filesetstring

A set of checkpoint files, configs, and other auxiliary info associated with this model - expected format {workspace}/{fileset_name}

trust_remote_codebooleanDefaults to false

Whether to trust remote code to load this model checkpoint.

base_modelstring

Link to another model which is used as a base for the current model

api_endpointobject

Data about the inference endpoint for this model

backend_formatenum or null

Inference API wire format expected by the backend. If unset, inference routing treats the model as OPENAI_CHAT.

adapterslist of objects

Adapters that have been created against this model

promptobject

Configuration for prompt engineering

custom_fieldsmap from strings to any

Custom fields for additional metadata

ownershipmap from strings to any

Ownership information for the model

model_providerslist of strings

List of ModelProvider workspace/name resource names that provide inference for this Model Entity

Errors

422

Unprocessable Entity Error