mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
added DPO
This commit is contained in:
Ashwin Bharambe
parent
7cade3acc3
commit
631328f556
4 changed files with 796 additions and 472 deletions
|
|
@ -299,7 +299,7 @@
|
|||
"parameters": []
|
||||
}
|
||||
},
|
||||
"/finetuning/job/artifacts": {
|
||||
"/post_training/job/artifacts": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
|
|
@ -307,14 +307,14 @@
|
|||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/FinetuningJobArtifactsResponse"
|
||||
"$ref": "#/components/schemas/PostTrainingJobArtifactsResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Finetuning"
|
||||
"PostTraining"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
|
|
@ -328,7 +328,7 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/finetuning/job/status": {
|
||||
"/post_training/job/status": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
|
|
@ -336,14 +336,14 @@
|
|||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/FinetuningJobStatusResponse"
|
||||
"$ref": "#/components/schemas/PostTrainingJobStatusResponse"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Finetuning"
|
||||
"PostTraining"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
|
|
@ -357,7 +357,7 @@
|
|||
]
|
||||
}
|
||||
},
|
||||
"/finetuning/job/logs": {
|
||||
"/post_training/job/logs": {
|
||||
"get": {
|
||||
"responses": {
|
||||
"200": {
|
||||
|
|
@ -365,14 +365,14 @@
|
|||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/FinetuningJobLogStream"
|
||||
"$ref": "#/components/schemas/PostTrainingJobLogStream"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"Finetuning"
|
||||
"PostTraining"
|
||||
],
|
||||
"parameters": [
|
||||
{
|
||||
|
|
@ -664,6 +664,29 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/post_training/preference_optimize/": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "OK"
|
||||
}
|
||||
},
|
||||
"tags": [
|
||||
"PostTraining"
|
||||
],
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/PostTrainingRLHFRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
"required": true
|
||||
}
|
||||
}
|
||||
},
|
||||
"/reward_scoring/score": {
|
||||
"post": {
|
||||
"responses": {
|
||||
|
|
@ -694,7 +717,7 @@
|
|||
}
|
||||
}
|
||||
},
|
||||
"/finetuning/text_generation/train": {
|
||||
"/post_training/supervised_fine_tune/": {
|
||||
"post": {
|
||||
"responses": {
|
||||
"200": {
|
||||
|
|
@ -702,14 +725,14 @@
|
|||
}
|
||||
},
|
||||
"tags": [
|
||||
"Finetuning"
|
||||
"PostTraining"
|
||||
],
|
||||
"parameters": [],
|
||||
"requestBody": {
|
||||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/FinetuningTrainRequest"
|
||||
"$ref": "#/components/schemas/PostTrainingSFTRequest"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
|
@ -1697,7 +1720,7 @@
|
|||
"name"
|
||||
]
|
||||
},
|
||||
"FinetuningJobArtifactsResponse": {
|
||||
"PostTrainingJobArtifactsResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"job_uuid": {
|
||||
|
|
@ -1730,7 +1753,7 @@
|
|||
],
|
||||
"title": "Artifacts of a finetuning job."
|
||||
},
|
||||
"FinetuningJobStatusResponse": {
|
||||
"PostTrainingJobStatusResponse": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"job_uuid": {
|
||||
|
|
@ -1810,7 +1833,7 @@
|
|||
],
|
||||
"title": "Status of a finetuning job."
|
||||
},
|
||||
"FinetuningJobLogStream": {
|
||||
"PostTrainingJobLogStream": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"job_uuid": {
|
||||
|
|
@ -2672,6 +2695,191 @@
|
|||
],
|
||||
"title": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold."
|
||||
},
|
||||
"DPOAlignmentConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"reward_scale": {
|
||||
"type": "number"
|
||||
},
|
||||
"reward_clip": {
|
||||
"type": "number"
|
||||
},
|
||||
"epsilon": {
|
||||
"type": "number"
|
||||
},
|
||||
"gamma": {
|
||||
"type": "number"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"reward_scale",
|
||||
"reward_clip",
|
||||
"epsilon",
|
||||
"gamma"
|
||||
]
|
||||
},
|
||||
"OptimizerConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"optimizer_type": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"adam",
|
||||
"adamw",
|
||||
"sgd"
|
||||
]
|
||||
},
|
||||
"lr": {
|
||||
"type": "number"
|
||||
},
|
||||
"lr_min": {
|
||||
"type": "number"
|
||||
},
|
||||
"weight_decay": {
|
||||
"type": "number"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"optimizer_type",
|
||||
"lr",
|
||||
"lr_min",
|
||||
"weight_decay"
|
||||
]
|
||||
},
|
||||
"PostTrainingRLHFRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"job_uuid": {
|
||||
"type": "string"
|
||||
},
|
||||
"finetuned_model": {
|
||||
"$ref": "#/components/schemas/URL"
|
||||
},
|
||||
"dataset": {
|
||||
"$ref": "#/components/schemas/Dataset"
|
||||
},
|
||||
"validation_dataset": {
|
||||
"$ref": "#/components/schemas/Dataset"
|
||||
},
|
||||
"algorithm": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"dpo"
|
||||
]
|
||||
},
|
||||
"algorithm_config": {
|
||||
"$ref": "#/components/schemas/DPOAlignmentConfig"
|
||||
},
|
||||
"optimizer_config": {
|
||||
"$ref": "#/components/schemas/OptimizerConfig"
|
||||
},
|
||||
"training_config": {
|
||||
"$ref": "#/components/schemas/TrainingConfig"
|
||||
},
|
||||
"hyperparam_search_config": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
},
|
||||
"logger_config": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"oneOf": [
|
||||
{
|
||||
"type": "null"
|
||||
},
|
||||
{
|
||||
"type": "boolean"
|
||||
},
|
||||
{
|
||||
"type": "number"
|
||||
},
|
||||
{
|
||||
"type": "string"
|
||||
},
|
||||
{
|
||||
"type": "array"
|
||||
},
|
||||
{
|
||||
"type": "object"
|
||||
}
|
||||
]
|
||||
}
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"job_uuid",
|
||||
"finetuned_model",
|
||||
"dataset",
|
||||
"validation_dataset",
|
||||
"algorithm",
|
||||
"algorithm_config",
|
||||
"optimizer_config",
|
||||
"training_config",
|
||||
"hyperparam_search_config",
|
||||
"logger_config"
|
||||
],
|
||||
"title": "Request to finetune a model."
|
||||
},
|
||||
"TrainingConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"n_epochs": {
|
||||
"type": "integer"
|
||||
},
|
||||
"batch_size": {
|
||||
"type": "integer"
|
||||
},
|
||||
"shuffle": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"n_iters": {
|
||||
"type": "integer"
|
||||
},
|
||||
"enable_activation_checkpointing": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"memory_efficient_fsdp_wrap": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"fsdp_cpu_offload": {
|
||||
"type": "boolean"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"n_epochs",
|
||||
"batch_size",
|
||||
"shuffle",
|
||||
"n_iters",
|
||||
"enable_activation_checkpointing",
|
||||
"memory_efficient_fsdp_wrap",
|
||||
"fsdp_cpu_offload"
|
||||
]
|
||||
},
|
||||
"RewardScoringRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
|
|
@ -2727,7 +2935,69 @@
|
|||
],
|
||||
"title": "Response from the reward scoring. Batch of (prompt, response, score) tuples that pass the threshold."
|
||||
},
|
||||
"FinetuningTrainRequest": {
|
||||
"DoraFinetuningConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"lora_attn_modules": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"apply_lora_to_mlp": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"apply_lora_to_output": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"rank": {
|
||||
"type": "integer"
|
||||
},
|
||||
"alpha": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"lora_attn_modules",
|
||||
"apply_lora_to_mlp",
|
||||
"apply_lora_to_output",
|
||||
"rank",
|
||||
"alpha"
|
||||
]
|
||||
},
|
||||
"LoraFinetuningConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"lora_attn_modules": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"apply_lora_to_mlp": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"apply_lora_to_output": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"rank": {
|
||||
"type": "integer"
|
||||
},
|
||||
"alpha": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"lora_attn_modules",
|
||||
"apply_lora_to_mlp",
|
||||
"apply_lora_to_output",
|
||||
"rank",
|
||||
"alpha"
|
||||
]
|
||||
},
|
||||
"PostTrainingSFTRequest": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"job_uuid": {
|
||||
|
|
@ -2761,66 +3031,10 @@
|
|||
"$ref": "#/components/schemas/LoraFinetuningConfig"
|
||||
},
|
||||
{
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"lora_attn_modules": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"apply_lora_to_mlp": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"apply_lora_to_output": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"rank": {
|
||||
"type": "integer"
|
||||
},
|
||||
"alpha": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"lora_attn_modules",
|
||||
"apply_lora_to_mlp",
|
||||
"apply_lora_to_output",
|
||||
"rank",
|
||||
"alpha"
|
||||
]
|
||||
"$ref": "#/components/schemas/QLoraFinetuningConfig"
|
||||
},
|
||||
{
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"lora_attn_modules": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"apply_lora_to_mlp": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"apply_lora_to_output": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"rank": {
|
||||
"type": "integer"
|
||||
},
|
||||
"alpha": {
|
||||
"type": "integer"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"lora_attn_modules",
|
||||
"apply_lora_to_mlp",
|
||||
"apply_lora_to_output",
|
||||
"rank",
|
||||
"alpha"
|
||||
]
|
||||
"$ref": "#/components/schemas/DoraFinetuningConfig"
|
||||
}
|
||||
]
|
||||
},
|
||||
|
|
@ -2896,7 +3110,7 @@
|
|||
],
|
||||
"title": "Request to finetune a model."
|
||||
},
|
||||
"LoraFinetuningConfig": {
|
||||
"QLoraFinetuningConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"lora_attn_modules": {
|
||||
|
|
@ -2926,71 +3140,6 @@
|
|||
"rank",
|
||||
"alpha"
|
||||
]
|
||||
},
|
||||
"OptimizerConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"optimizer_type": {
|
||||
"type": "string",
|
||||
"enum": [
|
||||
"adam",
|
||||
"adamw",
|
||||
"sgd"
|
||||
]
|
||||
},
|
||||
"lr": {
|
||||
"type": "number"
|
||||
},
|
||||
"lr_min": {
|
||||
"type": "number"
|
||||
},
|
||||
"weight_decay": {
|
||||
"type": "number"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"optimizer_type",
|
||||
"lr",
|
||||
"lr_min",
|
||||
"weight_decay"
|
||||
]
|
||||
},
|
||||
"TrainingConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"n_epochs": {
|
||||
"type": "integer"
|
||||
},
|
||||
"batch_size": {
|
||||
"type": "integer"
|
||||
},
|
||||
"shuffle": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"n_iters": {
|
||||
"type": "integer"
|
||||
},
|
||||
"enable_activation_checkpointing": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"memory_efficient_fsdp_wrap": {
|
||||
"type": "boolean"
|
||||
},
|
||||
"fsdp_cpu_offload": {
|
||||
"type": "boolean"
|
||||
}
|
||||
},
|
||||
"additionalProperties": false,
|
||||
"required": [
|
||||
"n_epochs",
|
||||
"batch_size",
|
||||
"shuffle",
|
||||
"n_iters",
|
||||
"enable_activation_checkpointing",
|
||||
"memory_efficient_fsdp_wrap",
|
||||
"fsdp_cpu_offload"
|
||||
]
|
||||
}
|
||||
},
|
||||
"responses": {}
|
||||
|
|
@ -3001,27 +3150,27 @@
|
|||
}
|
||||
],
|
||||
"tags": [
|
||||
{
|
||||
"name": "RewardScoring"
|
||||
},
|
||||
{
|
||||
"name": "MemoryBanks"
|
||||
},
|
||||
{
|
||||
"name": "SyntheticDataGeneration"
|
||||
},
|
||||
{
|
||||
"name": "Finetuning"
|
||||
},
|
||||
{
|
||||
"name": "AgenticSystem"
|
||||
},
|
||||
{
|
||||
"name": "RewardScoring"
|
||||
},
|
||||
{
|
||||
"name": "Inference"
|
||||
},
|
||||
{
|
||||
"name": "SyntheticDataGeneration"
|
||||
},
|
||||
{
|
||||
"name": "Datasets"
|
||||
},
|
||||
{
|
||||
"name": "PostTraining"
|
||||
},
|
||||
{
|
||||
"name": "MemoryBanks"
|
||||
},
|
||||
{
|
||||
"name": "ShieldConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/ShieldConfig\" />"
|
||||
|
|
@ -3075,16 +3224,16 @@
|
|||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/MemoryBank\" />"
|
||||
},
|
||||
{
|
||||
"name": "FinetuningJobArtifactsResponse",
|
||||
"description": "Artifacts of a finetuning job.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/FinetuningJobArtifactsResponse\" />"
|
||||
"name": "PostTrainingJobArtifactsResponse",
|
||||
"description": "Artifacts of a finetuning job.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/PostTrainingJobArtifactsResponse\" />"
|
||||
},
|
||||
{
|
||||
"name": "FinetuningJobStatusResponse",
|
||||
"description": "Status of a finetuning job.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/FinetuningJobStatusResponse\" />"
|
||||
"name": "PostTrainingJobStatusResponse",
|
||||
"description": "Status of a finetuning job.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/PostTrainingJobStatusResponse\" />"
|
||||
},
|
||||
{
|
||||
"name": "FinetuningJobLogStream",
|
||||
"description": "Stream of logs from a finetuning job.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/FinetuningJobLogStream\" />"
|
||||
"name": "PostTrainingJobLogStream",
|
||||
"description": "Stream of logs from a finetuning job.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/PostTrainingJobLogStream\" />"
|
||||
},
|
||||
{
|
||||
"name": "BatchChatCompletionRequest",
|
||||
|
|
@ -3138,6 +3287,22 @@
|
|||
"name": "SyntheticDataGenerationResponse",
|
||||
"description": "Response from the synthetic data generation. Batch of (prompt, response, score) tuples that pass the threshold.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/SyntheticDataGenerationResponse\" />"
|
||||
},
|
||||
{
|
||||
"name": "DPOAlignmentConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/DPOAlignmentConfig\" />"
|
||||
},
|
||||
{
|
||||
"name": "OptimizerConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/OptimizerConfig\" />"
|
||||
},
|
||||
{
|
||||
"name": "PostTrainingRLHFRequest",
|
||||
"description": "Request to finetune a model.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/PostTrainingRLHFRequest\" />"
|
||||
},
|
||||
{
|
||||
"name": "TrainingConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/TrainingConfig\" />"
|
||||
},
|
||||
{
|
||||
"name": "RewardScoringRequest",
|
||||
"description": "Request to score a reward function. A list of prompts and a list of responses per prompt.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/RewardScoringRequest\" />"
|
||||
|
|
@ -3147,20 +3312,20 @@
|
|||
"description": "Response from the reward scoring. Batch of (prompt, response, score) tuples that pass the threshold.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/RewardScoringResponse\" />"
|
||||
},
|
||||
{
|
||||
"name": "FinetuningTrainRequest",
|
||||
"description": "Request to finetune a model.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/FinetuningTrainRequest\" />"
|
||||
"name": "DoraFinetuningConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/DoraFinetuningConfig\" />"
|
||||
},
|
||||
{
|
||||
"name": "LoraFinetuningConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/LoraFinetuningConfig\" />"
|
||||
},
|
||||
{
|
||||
"name": "OptimizerConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/OptimizerConfig\" />"
|
||||
"name": "PostTrainingSFTRequest",
|
||||
"description": "Request to finetune a model.\n\n<SchemaDefinition schemaRef=\"#/components/schemas/PostTrainingSFTRequest\" />"
|
||||
},
|
||||
{
|
||||
"name": "TrainingConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/TrainingConfig\" />"
|
||||
"name": "QLoraFinetuningConfig",
|
||||
"description": "<SchemaDefinition schemaRef=\"#/components/schemas/QLoraFinetuningConfig\" />"
|
||||
}
|
||||
],
|
||||
"x-tagGroups": [
|
||||
|
|
@ -3169,9 +3334,9 @@
|
|||
"tags": [
|
||||
"AgenticSystem",
|
||||
"Datasets",
|
||||
"Finetuning",
|
||||
"Inference",
|
||||
"MemoryBanks",
|
||||
"PostTraining",
|
||||
"RewardScoring",
|
||||
"SyntheticDataGeneration"
|
||||
]
|
||||
|
|
@ -3195,18 +3360,22 @@
|
|||
"CompletionResponse",
|
||||
"CompletionResponseStreamChunk",
|
||||
"CreateDatasetRequest",
|
||||
"DPOAlignmentConfig",
|
||||
"Dataset",
|
||||
"Dialog",
|
||||
"FinetuningJobArtifactsResponse",
|
||||
"FinetuningJobLogStream",
|
||||
"FinetuningJobStatusResponse",
|
||||
"FinetuningTrainRequest",
|
||||
"DoraFinetuningConfig",
|
||||
"KScoredPromptGenerations",
|
||||
"LoraFinetuningConfig",
|
||||
"MemoryBank",
|
||||
"Message",
|
||||
"MessageScore",
|
||||
"OptimizerConfig",
|
||||
"PostTrainingJobArtifactsResponse",
|
||||
"PostTrainingJobLogStream",
|
||||
"PostTrainingJobStatusResponse",
|
||||
"PostTrainingRLHFRequest",
|
||||
"PostTrainingSFTRequest",
|
||||
"QLoraFinetuningConfig",
|
||||
"RewardScoringRequest",
|
||||
"RewardScoringResponse",
|
||||
"ShieldConfig",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue