Instructions to use AlgoDriveAI/Inferno-Exp-1.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlgoDriveAI/Inferno-Exp-1.5 with Transformers:

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

pipe = pipeline("text-generation", model="AlgoDriveAI/Inferno-Exp-1.5", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("AlgoDriveAI/Inferno-Exp-1.5", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AlgoDriveAI/Inferno-Exp-1.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlgoDriveAI/Inferno-Exp-1.5"
# 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-1.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AlgoDriveAI/Inferno-Exp-1.5

SGLang

How to use AlgoDriveAI/Inferno-Exp-1.5 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-1.5" \
    --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-1.5",
		"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-1.5" \
        --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-1.5",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AlgoDriveAI/Inferno-Exp-1.5 with Docker Model Runner:
```
docker model run hf.co/AlgoDriveAI/Inferno-Exp-1.5
```

AlgoDriveAI commited on 21 days ago

Commit

4b3de72

verified ·

1 Parent(s): 4461ac5

Transformers 5 compatibility: _tied_weights_keys as a {target: source} dict

Browse files

Files changed (1) hide show

modeling_inferno.py +1 -1

modeling_inferno.py CHANGED Viewed

@@ -99,7 +99,7 @@ class Block(nn.Module):
 class InfernoForCausalLM(PreTrainedModel, GenerationMixin):
     config_class = InfernoConfig
     base_model_prefix = "model"
-    _tied_weights_keys = ["lm_head.weight"]
     _no_split_modules = ["Block"]
     def __init__(self, config):

 class InfernoForCausalLM(PreTrainedModel, GenerationMixin):
     config_class = InfernoConfig
     base_model_prefix = "model"
+    _tied_weights_keys = {"lm_head.weight": "embed.weight"}   # {target: source}; works on Transformers 4 and 5
     _no_split_modules = ["Block"]
     def __init__(self, config):