llama-stack-mirror/llama_stack/templates/ollama/run-with-safety.yaml
Charlie Doern f02f7b28c1
feat: add huggingface post_training impl (#2132)
# What does this PR do?


adds an inline HF SFTTrainer provider. Alongside touchtune -- this is a
super popular option for running training jobs. The config allows a user
to specify some key fields such as a model, chat_template, device, etc

the provider comes with one recipe `finetune_single_device` which works
both with and without LoRA.

any model that is a valid HF identifier can be given and the model will
be pulled.

this has been tested so far with CPU and MPS device types, but should be
compatible with CUDA out of the box

The provider processes the given dataset into the proper format,
establishes the various steps per epoch, steps per save, steps per eval,
sets a sane SFTConfig, and runs n_epochs of training

if checkpoint_dir is none, no model is saved. If there is a checkpoint
dir, a model is saved every `save_steps` and at the end of training.


## Test Plan

re-enabled post_training integration test suite with a singular test
that loads the simpleqa dataset:
https://huggingface.co/datasets/llamastack/simpleqa and a tiny granite
model: https://huggingface.co/ibm-granite/granite-3.3-2b-instruct. The
test now uses the llama stack client and the proper post_training API

runs one step with a batch_size of 1. This test runs on CPU on the
Ubuntu runner so it needs to be a small batch and a single step.

[//]: # (## Documentation)

---------

Signed-off-by: Charlie Doern <cdoern@redhat.com>
2025-05-16 14:41:28 -07:00

147 lines
3.8 KiB
YAML

version: '2'
image_name: ollama
apis:
- agents
- datasetio
- eval
- inference
- post_training
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
inference:
- provider_id: ollama
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:http://localhost:11434}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/faiss_store.db
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config: {}
- provider_id: code-scanner
provider_type: inline::code-scanner
config: {}
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence_store:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/agents_store.db
telemetry:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
service_name: ${env.OTEL_SERVICE_NAME:}
sinks: ${env.TELEMETRY_SINKS:console,sqlite}
sqlite_db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/trace_store.db
eval:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/meta_reference_eval.db
datasetio:
- provider_id: huggingface
provider_type: remote::huggingface
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/huggingface_datasetio.db
- provider_id: localfs
provider_type: inline::localfs
config:
kvstore:
type: sqlite
namespace: null
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/localfs_datasetio.db
scoring:
- provider_id: basic
provider_type: inline::basic
config: {}
- provider_id: llm-as-judge
provider_type: inline::llm-as-judge
config: {}
- provider_id: braintrust
provider_type: inline::braintrust
config:
openai_api_key: ${env.OPENAI_API_KEY:}
post_training:
- provider_id: huggingface
provider_type: inline::huggingface
config:
checkpoint_format: huggingface
distributed_backend: null
device: cpu
tool_runtime:
- provider_id: brave-search
provider_type: remote::brave-search
config:
api_key: ${env.BRAVE_SEARCH_API_KEY:}
max_results: 3
- provider_id: tavily-search
provider_type: remote::tavily-search
config:
api_key: ${env.TAVILY_SEARCH_API_KEY:}
max_results: 3
- provider_id: rag-runtime
provider_type: inline::rag-runtime
config: {}
- provider_id: model-context-protocol
provider_type: remote::model-context-protocol
config: {}
- provider_id: wolfram-alpha
provider_type: remote::wolfram-alpha
config:
api_key: ${env.WOLFRAM_ALPHA_API_KEY:}
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/ollama}/registry.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}
provider_id: ollama
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL}
provider_id: ollama
model_type: llm
- metadata:
embedding_dimension: 384
model_id: all-MiniLM-L6-v2
provider_id: ollama
provider_model_id: all-minilm:latest
model_type: embedding
shields:
- shield_id: ${env.SAFETY_MODEL}
provider_id: llama-guard
- shield_id: CodeScanner
provider_id: code-scanner
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
provider_id: tavily-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
- toolgroup_id: builtin::wolfram_alpha
provider_id: wolfram-alpha
server:
port: 8321