Merge branch 'main' into inference_refactor

This commit is contained in:
Botao Chen 2024-12-17 20:10:23 -08:00
commit fadb7deae5
79 changed files with 1547 additions and 2026 deletions

View file

@ -886,7 +886,7 @@
},
{
"cell_type": "code",
"execution_count": 49,
"execution_count": null,
"id": "9496f75c",
"metadata": {
"colab": {
@ -896,30 +896,7 @@
"id": "9496f75c",
"outputId": "fb9a0610-896d-4ec1-8aac-691222db5ca0"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"User> hello\n",
"> Response: Hello. How can I assist you today?\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "Interrupted by user",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-49-bec9fae1b65b>\u001b[0m in \u001b[0;36m<cell line: 26>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 24\u001b[0m \u001b[0mconversation_history\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0massistant_message\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 25\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 26\u001b[0;31m \u001b[0mchat_loop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m<ipython-input-49-bec9fae1b65b>\u001b[0m in \u001b[0;36mchat_loop\u001b[0;34m()\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0mconversation_history\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0muser_input\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'User> '\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 7\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0muser_input\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlower\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32min\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m'exit'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'quit'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'bye'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[0mcprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'Ending conversation. Goodbye!'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'yellow'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/ipykernel/kernelbase.py\u001b[0m in \u001b[0;36mraw_input\u001b[0;34m(self, prompt)\u001b[0m\n\u001b[1;32m 849\u001b[0m \u001b[0;34m\"raw_input was called, but this frontend does not support input requests.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 850\u001b[0m )\n\u001b[0;32m--> 851\u001b[0;31m return self._input_request(str(prompt),\n\u001b[0m\u001b[1;32m 852\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parent_ident\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 853\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_parent_header\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/ipykernel/kernelbase.py\u001b[0m in \u001b[0;36m_input_request\u001b[0;34m(self, prompt, ident, parent, password)\u001b[0m\n\u001b[1;32m 893\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 894\u001b[0m \u001b[0;31m# re-raise KeyboardInterrupt, to truncate traceback\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 895\u001b[0;31m \u001b[0;32mraise\u001b[0m \u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Interrupted by user\"\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 896\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 897\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwarning\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Invalid Message:\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mexc_info\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: Interrupted by user"
]
}
],
"outputs": [],
"source": [
"from termcolor import cprint\n",
"\n",
@ -1026,7 +1003,8 @@
},
"source": [
"### 2.0. Structured Decoding\n",
"- You may use `response_format` to get a JSON structured output from the model."
"\n",
"You can use `response_format` to force the model into a \"guided decode\" mode where model tokens are forced to abide by a certain grammar. Currently only JSON grammars are supported."
]
},
{
@ -1097,7 +1075,8 @@
},
"source": [
"### 2.1. Safety API\n",
"- Llama Stack provides a Shield system that can be applied at multiple touchpoints."
"\n",
"Llama Stack provides Safety guardrails which can be applied at multiple touchpoints within an agentic application. "
]
},
{
@ -1234,15 +1213,14 @@
"]\n",
"\n",
"for p in safe_examples + unsafe_examples:\n",
" print(f\"Running on input : {p}\")\n",
" for message in [{\"content\": [p], \"role\": \"user\"}]:\n",
" response = client.safety.run_shield(\n",
" messages=[message],\n",
" shield_id=available_shields[0],\n",
" params={},\n",
" )\n",
"\n",
" pprint(response)"
" print(f\"Checking if input is safe: {p}\")\n",
" message = {\"content\": p, \"role\": \"user\"}\n",
" response = client.safety.run_shield(\n",
" messages=[message],\n",
" shield_id=available_shields[0],\n",
" params={},\n",
" )\n",
" pprint(response)"
]
},
{

View file

@ -23,9 +23,10 @@ from llama_models import schema_utils
# generation though, we need the full definitions and implementations from the
# (json-strong-typing) package.
from .strong_typing.schema import json_schema_type
from .strong_typing.schema import json_schema_type, register_schema
schema_utils.json_schema_type = json_schema_type
schema_utils.register_schema = register_schema
from llama_stack.apis.version import LLAMA_STACK_API_VERSION # noqa: E402
from llama_stack.distribution.stack import LlamaStack # noqa: E402

File diff suppressed because it is too large Load diff

View file

@ -275,11 +275,9 @@ components:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- $ref: '#/components/schemas/InterleavedContentItem'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
$ref: '#/components/schemas/InterleavedContentItem'
type: array
- $ref: '#/components/schemas/URL'
mime_type:
@ -353,14 +351,7 @@ components:
properties:
content_batch:
items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
type: array
logprobs:
additionalProperties: false
@ -575,14 +566,7 @@ components:
additionalProperties: false
properties:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
role:
const: assistant
default: assistant
@ -603,14 +587,7 @@ components:
additionalProperties: false
properties:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
logprobs:
additionalProperties: false
properties:
@ -788,97 +765,7 @@ components:
properties:
dataset_schema:
additionalProperties:
oneOf:
- additionalProperties: false
properties:
type:
const: string
default: string
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: number
default: number
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: boolean
default: boolean
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: array
default: array
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: object
default: object
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: json
default: json
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: union
default: union
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: chat_completion_input
default: chat_completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: completion_input
default: completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: agent_turn_input
default: agent_turn_input
type: string
required:
- type
type: object
$ref: '#/components/schemas/ParamType'
type: object
identifier:
type: string
@ -951,14 +838,7 @@ components:
properties:
contents:
items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
type: array
model_id:
type: string
@ -1159,22 +1039,20 @@ components:
required:
- status
type: object
ImageMedia:
ImageContentItem:
additionalProperties: false
properties:
image:
oneOf:
- additionalProperties: false
properties:
format:
type: string
format_description:
type: string
title: This class represents an image object. To create
type: object
- $ref: '#/components/schemas/URL'
data:
contentEncoding: base64
type: string
type:
const: image
default: image
type: string
url:
$ref: '#/components/schemas/URL'
required:
- image
- type
type: object
InferenceStep:
additionalProperties: false
@ -1216,6 +1094,17 @@ components:
- bank_id
- documents
type: object
InterleavedContent:
oneOf:
- type: string
- $ref: '#/components/schemas/InterleavedContentItem'
- items:
$ref: '#/components/schemas/InterleavedContentItem'
type: array
InterleavedContentItem:
oneOf:
- $ref: '#/components/schemas/ImageContentItem'
- $ref: '#/components/schemas/TextContentItem'
Job:
additionalProperties: false
properties:
@ -1395,11 +1284,9 @@ components:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- $ref: '#/components/schemas/InterleavedContentItem'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
$ref: '#/components/schemas/InterleavedContentItem'
type: array
- $ref: '#/components/schemas/URL'
document_id:
@ -1428,14 +1315,7 @@ components:
format: date-time
type: string
inserted_context:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
memory_bank_ids:
items:
type: string
@ -1731,6 +1611,98 @@ components:
- rows
- total_count
type: object
ParamType:
oneOf:
- additionalProperties: false
properties:
type:
const: string
default: string
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: number
default: number
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: boolean
default: boolean
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: array
default: array
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: object
default: object
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: json
default: json
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: union
default: union
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: chat_completion_input
default: chat_completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: completion_input
default: completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: agent_turn_input
default: agent_turn_input
type: string
required:
- type
type: object
PhotogenToolDefinition:
additionalProperties: false
properties:
@ -1918,14 +1890,7 @@ components:
- type: object
type: object
query:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
required:
- bank_id
- query
@ -1938,14 +1903,7 @@ components:
additionalProperties: false
properties:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
document_id:
type: string
token_count:
@ -2022,97 +1980,7 @@ components:
type: string
dataset_schema:
additionalProperties:
oneOf:
- additionalProperties: false
properties:
type:
const: string
default: string
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: number
default: number
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: boolean
default: boolean
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: array
default: array
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: object
default: object
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: json
default: json
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: union
default: union
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: chat_completion_input
default: chat_completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: completion_input
default: completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: agent_turn_input
default: agent_turn_input
type: string
required:
- type
type: object
$ref: '#/components/schemas/ParamType'
type: object
metadata:
additionalProperties:
@ -2223,97 +2091,7 @@ components:
provider_scoring_fn_id:
type: string
return_type:
oneOf:
- additionalProperties: false
properties:
type:
const: string
default: string
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: number
default: number
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: boolean
default: boolean
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: array
default: array
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: object
default: object
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: json
default: json
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: union
default: union
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: chat_completion_input
default: chat_completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: completion_input
default: completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: agent_turn_input
default: agent_turn_input
type: string
required:
- type
type: object
$ref: '#/components/schemas/ParamType'
scoring_fn_id:
type: string
required:
@ -2623,97 +2401,7 @@ components:
provider_resource_id:
type: string
return_type:
oneOf:
- additionalProperties: false
properties:
type:
const: string
default: string
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: number
default: number
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: boolean
default: boolean
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: array
default: array
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: object
default: object
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: json
default: json
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: union
default: union
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: chat_completion_input
default: chat_completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: completion_input
default: completion_input
type: string
required:
- type
type: object
- additionalProperties: false
properties:
type:
const: agent_turn_input
default: agent_turn_input
type: string
required:
- type
type: object
$ref: '#/components/schemas/ParamType'
type:
const: scoring_function
default: scoring_function
@ -3112,14 +2800,7 @@ components:
additionalProperties: false
properties:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
role:
const: system
default: system
@ -3128,6 +2809,19 @@ components:
- role
- content
type: object
TextContentItem:
additionalProperties: false
properties:
text:
type: string
type:
const: text
default: text
type: string
required:
- type
- text
type: object
TokenLogProbs:
additionalProperties: false
properties:
@ -3293,14 +2987,7 @@ components:
call_id:
type: string
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
tool_name:
oneOf:
- $ref: '#/components/schemas/BuiltinTool'
@ -3316,14 +3003,7 @@ components:
call_id:
type: string
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
role:
const: ipython
default: ipython
@ -3492,23 +3172,9 @@ components:
additionalProperties: false
properties:
content:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
context:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
- items:
oneOf:
- type: string
- $ref: '#/components/schemas/ImageMedia'
type: array
$ref: '#/components/schemas/InterleavedContent'
role:
const: user
default: user
@ -5297,8 +4963,9 @@ tags:
name: GraphMemoryBankParams
- description: <SchemaDefinition schemaRef="#/components/schemas/HealthInfo" />
name: HealthInfo
- description: <SchemaDefinition schemaRef="#/components/schemas/ImageMedia" />
name: ImageMedia
- description: <SchemaDefinition schemaRef="#/components/schemas/ImageContentItem"
/>
name: ImageContentItem
- name: Inference
- description: <SchemaDefinition schemaRef="#/components/schemas/InferenceStep" />
name: InferenceStep
@ -5306,6 +4973,12 @@ tags:
/>
name: InsertDocumentsRequest
- name: Inspect
- description: <SchemaDefinition schemaRef="#/components/schemas/InterleavedContent"
/>
name: InterleavedContent
- description: <SchemaDefinition schemaRef="#/components/schemas/InterleavedContentItem"
/>
name: InterleavedContentItem
- description: <SchemaDefinition schemaRef="#/components/schemas/Job" />
name: Job
- description: <SchemaDefinition schemaRef="#/components/schemas/JobCancelRequest"
@ -5364,6 +5037,8 @@ tags:
- description: <SchemaDefinition schemaRef="#/components/schemas/PaginatedRowsResult"
/>
name: PaginatedRowsResult
- description: <SchemaDefinition schemaRef="#/components/schemas/ParamType" />
name: ParamType
- description: <SchemaDefinition schemaRef="#/components/schemas/PhotogenToolDefinition"
/>
name: PhotogenToolDefinition
@ -5521,6 +5196,9 @@ tags:
- description: <SchemaDefinition schemaRef="#/components/schemas/SystemMessage" />
name: SystemMessage
- name: Telemetry
- description: <SchemaDefinition schemaRef="#/components/schemas/TextContentItem"
/>
name: TextContentItem
- description: <SchemaDefinition schemaRef="#/components/schemas/TokenLogProbs" />
name: TokenLogProbs
- description: <SchemaDefinition schemaRef="#/components/schemas/ToolCall" />
@ -5670,9 +5348,11 @@ x-tagGroups:
- GraphMemoryBank
- GraphMemoryBankParams
- HealthInfo
- ImageMedia
- ImageContentItem
- InferenceStep
- InsertDocumentsRequest
- InterleavedContent
- InterleavedContentItem
- Job
- JobCancelRequest
- JobStatus
@ -5694,6 +5374,7 @@ x-tagGroups:
- OptimizerConfig
- OptimizerType
- PaginatedRowsResult
- ParamType
- PhotogenToolDefinition
- PostTrainingJob
- PostTrainingJobArtifactsResponse
@ -5745,6 +5426,7 @@ x-tagGroups:
- SyntheticDataGenerateRequest
- SyntheticDataGenerationResponse
- SystemMessage
- TextContentItem
- TokenLogProbs
- ToolCall
- ToolCallDelta

View file

@ -23,7 +23,7 @@ The following environment variables can be configured:
The following models are available by default:
- `meta-llama/Llama-3.1-8B-Instruct (llama3.1-8b)`
- `meta-llama/Llama-3.1-70B-Instruct (llama3.1-70b)`
- `meta-llama/Llama-3.3-70B-Instruct (llama-3.3-70b)`
### Prerequisite: API Keys