Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion models/groq/gpt-oss-120b.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -77,7 +77,6 @@ params:
description: Controls how reasoning tokens are returned — hidden from the response, raw within the content, or parsed into a separate field.
values:
- hidden
- raw
- parsed
group: reasoning
- path: response_format.type
Expand Down
51 changes: 51 additions & 0 deletions models/nvidia/mistral-nemotron.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
provider: nvidia
authType: api_key
apiSurface: openai-chat-completions
model: mistral-nemotron
wireId: mistralai/mistral-nemotron
params:
- path: temperature
type: number
label: Temperature
description: Controls randomness. Lower values make outputs more focused; higher values make them more varied. Not recommended to modify both temperature and top_p in the same call.
default: 0.6
range:
min: 0
max: 1
group: sampling
- path: top_p
type: number
label: Top P
description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability. Not recommended to modify both temperature and top_p in the same call.
default: 0.95
range:
max: 1
group: sampling
- path: max_tokens
type: integer
label: Max tokens
description: Maximum number of tokens to generate. Generation stops when this limit is reached.
default: 4096
range:
min: 1
max: 16384
group: generation_length
- path: frequency_penalty
type: number
label: Frequency penalty
description: Penalizes new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
default: 0
range:
min: -2
max: 2
group: sampling
- path: presence_penalty
type: number
label: Presence penalty
description: Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.
default: 0
range:
min: -2
max: 2
group: sampling
56 changes: 56 additions & 0 deletions models/opencode-go/minimax-m2.7-subscription.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,56 @@
# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json
provider: opencode-go
authType: subscription
apiSurface: openai-chat-completions
model: minimax-m2.7
wireId: opencode-go/minimax-m2.7
params:
- path: max_tokens
type: integer
label: Max tokens
description: Maximum number of tokens to generate in the response.
range:
min: 1
group: generation_length
- path: top_p
type: number
label: Top P
description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
range:
min: 0.01
max: 1
step: 0.01
group: sampling
- path: top_k
type: integer
label: Top K
description: Limits token sampling to the top K most likely next tokens.
range:
min: 1
group: sampling
- path: presence_penalty
type: number
label: Presence penalty
description: Penalizes tokens that have already appeared to encourage a wider variety of content.
range:
min: -2
max: 2
step: 0.1
group: sampling
- path: frequency_penalty
type: number
label: Frequency penalty
description: Penalizes tokens in proportion to how often they have already appeared.
range:
min: -2
max: 2
step: 0.1
group: sampling
- path: response_format.type
type: enum
label: Response format
description: Choose plain text or force valid JSON output.
values:
- text
- json_object
group: output_format
2 changes: 1 addition & 1 deletion models/xai/grok-4.3.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ params:
description: Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.
default: 1
range:
min: 0
min: 0.01
max: 1
step: 0.01
group: sampling
Expand Down
147 changes: 145 additions & 2 deletions packages/modelparams-python/src/modelparams/_generated/catalog.json
Original file line number Diff line number Diff line change
Expand Up @@ -19462,7 +19462,6 @@
"type": "enum",
"values": [
"hidden",
"raw",
"parsed"
]
},
Expand Down Expand Up @@ -26908,6 +26907,74 @@
}
]
},
{
"provider": "nvidia",
"authType": "api_key",
"apiSurface": "openai-chat-completions",
"model": "mistral-nemotron",
"wireId": "mistralai/mistral-nemotron",
"params": [
{
"path": "temperature",
"label": "Temperature",
"description": "Controls randomness. Lower values make outputs more focused; higher values make them more varied. Not recommended to modify both temperature and top_p in the same call.",
"group": "sampling",
"type": "number",
"default": 0.6,
"range": {
"min": 0,
"max": 1
}
},
{
"path": "top_p",
"label": "Top P",
"description": "Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability. Not recommended to modify both temperature and top_p in the same call.",
"group": "sampling",
"type": "number",
"default": 0.95,
"range": {
"max": 1
}
},
{
"path": "max_tokens",
"label": "Max tokens",
"description": "Maximum number of tokens to generate. Generation stops when this limit is reached.",
"group": "generation_length",
"type": "integer",
"default": 4096,
"range": {
"min": 1,
"max": 16384
}
},
{
"path": "frequency_penalty",
"label": "Frequency penalty",
"description": "Penalizes new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.",
"group": "sampling",
"type": "number",
"default": 0,
"range": {
"min": -2,
"max": 2
}
},
{
"path": "presence_penalty",
"label": "Presence penalty",
"description": "Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.",
"group": "sampling",
"type": "number",
"default": 0,
"range": {
"min": -2,
"max": 2
}
}
]
},
{
"provider": "nvidia",
"authType": "api_key",
Expand Down Expand Up @@ -31314,6 +31381,82 @@
}
]
},
{
"provider": "opencode-go",
"authType": "subscription",
"apiSurface": "openai-chat-completions",
"model": "minimax-m2.7",
"wireId": "opencode-go/minimax-m2.7",
"params": [
{
"path": "max_tokens",
"label": "Max tokens",
"description": "Maximum number of tokens to generate in the response.",
"group": "generation_length",
"type": "integer",
"range": {
"min": 1
}
},
{
"path": "top_p",
"label": "Top P",
"description": "Controls nucleus sampling by limiting generation to tokens within the selected cumulative probability.",
"group": "sampling",
"type": "number",
"range": {
"min": 0.01,
"max": 1,
"step": 0.01
}
},
{
"path": "top_k",
"label": "Top K",
"description": "Limits token sampling to the top K most likely next tokens.",
"group": "sampling",
"type": "integer",
"range": {
"min": 1
}
},
{
"path": "presence_penalty",
"label": "Presence penalty",
"description": "Penalizes tokens that have already appeared to encourage a wider variety of content.",
"group": "sampling",
"type": "number",
"range": {
"min": -2,
"max": 2,
"step": 0.1
}
},
{
"path": "frequency_penalty",
"label": "Frequency penalty",
"description": "Penalizes tokens in proportion to how often they have already appeared.",
"group": "sampling",
"type": "number",
"range": {
"min": -2,
"max": 2,
"step": 0.1
}
},
{
"path": "response_format.type",
"label": "Response format",
"description": "Choose plain text or force valid JSON output.",
"group": "output_format",
"type": "enum",
"values": [
"text",
"json_object"
]
}
]
},
{
"provider": "opencode-go",
"authType": "subscription",
Expand Down Expand Up @@ -34239,7 +34382,7 @@
"type": "number",
"default": 1,
"range": {
"min": 0,
"min": 0.01,
"max": 1,
"step": 0.01
}
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -337,6 +337,7 @@
"nvidia/llama-3.3-nemotron-super-49b-v1",
"nvidia/llama-3.3-nemotron-super-49b-v1.5",
"nvidia/minimax-m3",
"nvidia/mistral-nemotron",
"nvidia/muse-glimmer-30b",
"nvidia/nemoguard-jailbreak-detect",
"nvidia/nemotron-3-nano-30b-a3b",
Expand Down Expand Up @@ -421,6 +422,7 @@
"opencode-go/longcat-2.5-preview-free-subscription",
"opencode-go/mimo-v2.6-flash-subscription",
"opencode-go/mimo-v2.6-pro-subscription",
"opencode-go/minimax-m2.7-subscription",
"opencode-go/omen-alpha-subscription",
"opencode-go/qwen3.8-flash-subscription",
"opencode-go/qwen3.8-max-subscription",
Expand Down Expand Up @@ -818,6 +820,7 @@
"nvidia/llama-3.3-nemotron-super-49b-v1",
"nvidia/llama-3.3-nemotron-super-49b-v1.5",
"nvidia/minimax-m3",
"nvidia/mistral-nemotron",
"nvidia/muse-glimmer-30b",
"nvidia/nemoguard-jailbreak-detect",
"nvidia/nemotron-3-nano-30b-a3b",
Expand Down Expand Up @@ -902,6 +905,7 @@
"opencode-go/longcat-2.5-preview-free-subscription",
"opencode-go/mimo-v2.6-flash-subscription",
"opencode-go/mimo-v2.6-pro-subscription",
"opencode-go/minimax-m2.7-subscription",
"opencode-go/omen-alpha-subscription",
"opencode-go/qwen3.8-flash-subscription",
"opencode-go/qwen3.8-max-subscription",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -362,6 +362,7 @@
"nvidia/llama-3.3-nemotron-super-49b-v1": nvidia.Llama_3_3_Nemotron_Super_49b_V1Params,
"nvidia/llama-3.3-nemotron-super-49b-v1.5": nvidia.Llama_3_3_Nemotron_Super_49b_V1_5Params,
"nvidia/minimax-m3": nvidia.Minimax_M3Params,
"nvidia/mistral-nemotron": nvidia.Mistral_NemotronParams,
"nvidia/muse-glimmer-30b": nvidia.Muse_Glimmer_30bParams,
"nvidia/nemoguard-jailbreak-detect": nvidia.Nemoguard_Jailbreak_DetectParams,
"nvidia/nemotron-3-nano-30b-a3b": nvidia.Nemotron_3_Nano_30b_A3bParams,
Expand Down Expand Up @@ -446,6 +447,7 @@
"opencode-go/longcat-2.5-preview-free-subscription": opencode_go.Longcat_2_5_Preview_Free_SubscriptionParams,
"opencode-go/mimo-v2.6-flash-subscription": opencode_go.Mimo_V2_6_Flash_SubscriptionParams,
"opencode-go/mimo-v2.6-pro-subscription": opencode_go.Mimo_V2_6_Pro_SubscriptionParams,
"opencode-go/minimax-m2.7-subscription": opencode_go.Minimax_M2_7_SubscriptionParams,
"opencode-go/omen-alpha-subscription": opencode_go.Omen_Alpha_SubscriptionParams,
"opencode-go/qwen3.8-flash-subscription": opencode_go.Qwen3_8_Flash_SubscriptionParams,
"opencode-go/qwen3.8-max-subscription": opencode_go.Qwen3_8_Max_SubscriptionParams,
Expand Down
2 changes: 1 addition & 1 deletion packages/modelparams-python/src/modelparams/types/groq.py
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@
"seed": int,
"stop": str,
"reasoning_effort": Literal["none", "default"],
"reasoning_format": Literal["hidden", "raw", "parsed"],
"reasoning_format": Literal["hidden", "parsed"],
"response_format.type": Literal["text", "json_object"],
},
total=False,
Expand Down
14 changes: 14 additions & 0 deletions packages/modelparams-python/src/modelparams/types/nvidia.py
Original file line number Diff line number Diff line change
Expand Up @@ -266,6 +266,19 @@
)
setattr(Minimax_M3Params, "__pydantic_config__", _PARAMS_CONFIG)

Mistral_NemotronParams = TypedDict(
"Mistral_NemotronParams",
{
"temperature": Annotated[float, Field(ge=0, le=1)],
"top_p": Annotated[float, Field(le=1)],
"max_tokens": Annotated[int, Field(ge=1, le=16384)],
"frequency_penalty": Annotated[float, Field(ge=-2, le=2)],
"presence_penalty": Annotated[float, Field(ge=-2, le=2)],
},
total=False,
)
setattr(Mistral_NemotronParams, "__pydantic_config__", _PARAMS_CONFIG)

Muse_Glimmer_30bParams = TypedDict(
"Muse_Glimmer_30bParams",
{
Expand Down Expand Up @@ -443,6 +456,7 @@
"Llama_3_3_Nemotron_Super_49b_V1Params",
"Llama_3_3_Nemotron_Super_49b_V1_5Params",
"Minimax_M3Params",
"Mistral_NemotronParams",
"Muse_Glimmer_30bParams",
"Nemoguard_Jailbreak_DetectParams",
"Nemotron_3_Nano_30b_A3bParams",
Expand Down
Loading
Loading