Fine-tune GLiNER

This guide creates a config training job. You provide a ready dataset and training settings; Fastino runs the training loop.

Before you begin

Set FASTINO_API_KEY as shown in the Training API overview. The examples send it in the X-API-Key header and use jq to read JSON responses.

1. Choose the task

Extraction

Train GLiNER to find labeled spans such as people, products, or locations. Prepare text and entities rows and upload the dataset as NER data.

Classification

Train GLiNER to assign one or more labels to text. Prepare text with label or labels rows and upload the dataset as classification data.

Keep one row shape throughout each JSONL file. Follow Prepare and upload training datasets for the exact GLiNER JSONL formats, upload-URL request, file upload, processing request, and readiness check. Continue only after the dataset version reports ready.

2. Query trainable models

Do not hard-code a base model from an old example. Query the live catalog immediately before creating the job:

curl -sS "https://api.fastino.ai/v1/base-models?supports_training=true" \
  -H "X-API-Key: $FASTINO_API_KEY" | jq

Choose a GLiNER model that supports your task and desired training type. Copy its exact ID for the native Training API’s base_model field.

3. Create a config job

Replace the catalog model, dataset name, and version below.

curl -sS -X POST "https://api.fastino.ai/v1/training/jobs" \
  -H "X-API-Key: $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "support-request-extractor",
    "base_model": "BASE_MODEL_ID_FROM_CATALOG",
    "datasets": [
      {
        "name": "READY_DATASET_NAME",
        "version": "VERSION_NUMBER"
      }
    ],
    "training_type": "lora"
  }' | tee training-job.json

The response is the created job record. Save its id:

export TRAINING_JOB_ID="$(jq -r '.id' training-job.json)"
test "$TRAINING_JOB_ID" != "null"

See the create-job API reference for optional config-job fields.

4. Poll the job

Poll GET /v1/training/jobs/{job_id} until is_terminal_status is true:

while true; do
  if ! JOB="$(
    curl --fail-with-body -sS \
      "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID" \
      -H "X-API-Key: $FASTINO_API_KEY"
  )"; then
    echo "Could not read training job" >&2
    exit 1
  fi

  echo "$JOB" | jq -e 'has("is_terminal_status")' >/dev/null || {
    echo "Training response has no terminal-state field" >&2
    exit 1
  }

  echo "$JOB" | jq '{
    normalized_status,
    is_terminal_status,
    error_message,
    is_deployable,
    deployability_reason
  }'

  [ "$(echo "$JOB" | jq -r '.is_terminal_status')" = "true" ] && break
  sleep 10
done

For the config-job statuses and terminal-state guidance, see the Training API overview.

5. Inspect logs and checkpoints

Read logs when you need progress or failure details:

curl -sS \
  "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/logs" \
  -H "X-API-Key: $FASTINO_API_KEY" | jq

List the checkpoints Fastino created:

curl -sS \
  "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/checkpoints" \
  -H "X-API-Key: $FASTINO_API_KEY" | tee training-checkpoints.json | jq

export CHECKPOINT_ID="$(
  jq -r '[.checkpoints[] | select(.is_deployable == true)] | first | .id // empty' \
    training-checkpoints.json
)"
test -n "$CHECKPOINT_ID"

See logs and checkpoints for their response fields.

6. Deploy the trained model

Check the completed job’s is_deployable and deployability_reason fields, then deploy the selected deployable checkpoint:

curl --fail-with-body -sS -X POST \
  "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/checkpoints/$CHECKPOINT_ID/deploy" \
  -H "X-API-Key: $FASTINO_API_KEY" | jq

Poll the job again until its deployment state is ready. The training job ID is the model identifier used for hosted inference.

7. Run GLiNER inference

curl --fail-with-body -sS \
  "https://api.fastino.ai/v1/chat/completions" \
  -H "Authorization: Bearer $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"model\": \"$TRAINING_JOB_ID\",
    \"messages\": [
      {
        \"role\": \"user\",
        \"content\": \"Ada Lovelace worked in London.\"
      }
    ],
    \"schema\": {
      \"entities\": [
        {\"name\": \"person\"},
        {\"name\": \"location\"}
      ]
    }
  }" | jq -r '.choices[0].message.content | fromjson'

Call GLiNER

Use GLiNER for extraction or classification through POST /v1/chat/completions.

Install the GLiNER agent skill

Optionally give Cursor, Claude Code, or Codex the hosted GLiNER workflow.

Get Started

Decision Models

Entity & Classification

Training API

Inference API

Troubleshooting

SDK Integrations

Models

Account

Before you begin

1. Choose the task

Extraction

Classification

2. Query trainable models

3. Create a config job

4. Poll the job

5. Inspect logs and checkpoints

6. Deploy the trained model

7. Run GLiNER inference

Call GLiNER

Install the GLiNER agent skill

​Before you begin

​1. Choose the task

Extraction

Classification

​2. Query trainable models

​3. Create a config job

​4. Poll the job

​5. Inspect logs and checkpoints

​6. Deploy the trained model

​7. Run GLiNER inference

Call GLiNER

Install the GLiNER agent skill

Before you begin

1. Choose the task

2. Query trainable models

3. Create a config job

4. Poll the job

5. Inspect logs and checkpoints

6. Deploy the trained model

7. Run GLiNER inference