Instructions to use AlgoDriveAI/Inferno-Exp-1.7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlgoDriveAI/Inferno-Exp-1.7 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AlgoDriveAI/Inferno-Exp-1.7", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AlgoDriveAI/Inferno-Exp-1.7", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AlgoDriveAI/Inferno-Exp-1.7 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlgoDriveAI/Inferno-Exp-1.7"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlgoDriveAI/Inferno-Exp-1.7",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AlgoDriveAI/Inferno-Exp-1.7

SGLang

How to use AlgoDriveAI/Inferno-Exp-1.7 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AlgoDriveAI/Inferno-Exp-1.7" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlgoDriveAI/Inferno-Exp-1.7",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AlgoDriveAI/Inferno-Exp-1.7" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlgoDriveAI/Inferno-Exp-1.7",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AlgoDriveAI/Inferno-Exp-1.7 with Docker Model Runner:
```
docker model run hf.co/AlgoDriveAI/Inferno-Exp-1.7
```

AlgoDriveAI commited on 1 day ago

Commit

f43165d

verified ·

1 Parent(s): ea77415

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -482,9 +482,6 @@ These are different tokenization paths, not different weights. The slow-tokenize
 retained in `evaluation/arithmark-3_slow-tokenizer-reference.json` and is not mixed into the
 primary result. In this release, the actual tokenizer class is recorded explicitly.
-- [`training/checkpoint_provenance.json`](training/checkpoint_provenance.json): checkpoint SHA-256,
-  step, token progress, data identity and model-code fingerprint, where present.
-- [`training/tokenizer/`](training/tokenizer/): original training tokenizer files, unchanged.
 - [`evaluation/evaluate_arithmark3.py`](evaluation/evaluate_arithmark3.py): standalone evaluation runner
   configured for this exact snapshot.
 - [`release_manifest.json`](release_manifest.json): SHA-256 and size for every release artifact.
@@ -492,11 +489,11 @@ primary result. In this release, the actual tokenizer class is recorded explicit
 Exact supplied training source SHA-256: `ce792e3792a02edc3f31584294f4dfc68282d2f07f945168ec7ec905abf305f9`.
 The source is supplied for reproducibility; its historical default settings are not rewritten to
 pretend they were the saved checkpoint configuration. The released inference weights omit
-optimizer/RNG state; the original full training checkpoint remains on Drive.
 The root tokenizer uses the same vocabulary/EOS as training, with automatic BOS insertion
 disabled and BOS set to the training document EOS for tools that need a start-token ID,
-following the 1.6 export. The original tokenizer files remain under `training/tokenizer/`.
 ## Limitations

 retained in `evaluation/arithmark-3_slow-tokenizer-reference.json` and is not mixed into the
 primary result. In this release, the actual tokenizer class is recorded explicitly.
 - [`evaluation/evaluate_arithmark3.py`](evaluation/evaluate_arithmark3.py): standalone evaluation runner
   configured for this exact snapshot.
 - [`release_manifest.json`](release_manifest.json): SHA-256 and size for every release artifact.
 Exact supplied training source SHA-256: `ce792e3792a02edc3f31584294f4dfc68282d2f07f945168ec7ec905abf305f9`.
 The source is supplied for reproducibility; its historical default settings are not rewritten to
 pretend they were the saved checkpoint configuration. The released inference weights omit
+optimizer/RNG state.
 The root tokenizer uses the same vocabulary/EOS as training, with automatic BOS insertion
 disabled and BOS set to the training document EOS for tools that need a start-token ID,
+following the 1.6 export.
 ## Limitations