@tuned-tensor/cli 0.4.11 → 0.4.13

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -100,6 +100,9 @@ tt models base
100
100
  tt models list
101
101
  tt models get <model-id>
102
102
  tt models download <model-id> --output model.tar.gz
103
+ tt models setup-runtime
104
+ tt models serve <model-id> --spec tunedtensor.json
105
+ tt models serve ./model --port 8000
103
106
  ```
104
107
 
105
108
  Use `--dataset <dataset-id-or-prefix>` with `tt runs start` to train from an uploaded dataset instead of inline spec examples. Add `--train-ratio`, `--validation-ratio`, and `--test-ratio` to override the default 80/10/10 split.
@@ -108,7 +111,22 @@ Use `--max-eval-examples <n>` and `--max-test-eval-examples <n>` with `tt runs s
108
111
 
109
112
  Use `--no-llm-judge` with `tt runs start` to opt out of LLM judging for a new run.
110
113
 
111
- `tt models download` downloads models that have a Tuned Tensor-hosted artifact. Hosted models can still be used for inference through their model ID, but may not expose downloadable weights.
114
+ `tt models download` downloads models that have a Tuned Tensor-hosted artifact. In interactive terminals it shows download progress, transfer rate, and ETA; `--json` output remains machine-readable. Hosted models can still be used for inference through their model ID, but may not expose downloadable weights.
115
+
116
+ `tt models setup-runtime` installs an isolated local Python runtime for reference serving. It chooses Python 3.10-3.12, creates a managed venv in the Tuned Tensor cache, and installs `torch`, `transformers`, `accelerate`, and `safetensors`. This can take a few minutes the first time.
117
+
118
+ `tt models serve` starts a local OpenAI-compatible reference server for a model ID, an extracted model directory, or a `.tar.gz` artifact. It auto-detects `tunedtensor.json` in the current directory or model directory and applies the compiled behavior spec as the default system prompt, so inference matches the prompt contract used during training. Use `--spec <path>` to point at a specific spec, or `--no-spec-prompt` when you intentionally want raw model behavior. If no compatible Python serving runtime is available, run `tt models setup-runtime` first.
119
+
120
+ ```bash
121
+ tt models setup-runtime
122
+ tt models serve <model-id> --spec tunedtensor.json
123
+ tt models serve <model-id> --spec tunedtensor.json --device mps # Apple Silicon
124
+ tt models serve <model-id> --spec tunedtensor.json --device cuda # NVIDIA GPU
125
+
126
+ curl http://127.0.0.1:8000/v1/chat/completions \
127
+ -H 'content-type: application/json' \
128
+ -d '{"messages":[{"role":"user","content":"Hello"}]}'
129
+ ```
112
130
 
113
131
  ## Billing & Credits
114
132