Instructions to use user-anto/Axiom-Dense-380M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use user-anto/Axiom-Dense-380M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="user-anto/Axiom-Dense-380M-Instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("user-anto/Axiom-Dense-380M-Instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use user-anto/Axiom-Dense-380M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "user-anto/Axiom-Dense-380M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "user-anto/Axiom-Dense-380M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/user-anto/Axiom-Dense-380M-Instruct

SGLang

How to use user-anto/Axiom-Dense-380M-Instruct 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 "user-anto/Axiom-Dense-380M-Instruct" \
    --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": "user-anto/Axiom-Dense-380M-Instruct",
		"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 "user-anto/Axiom-Dense-380M-Instruct" \
        --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": "user-anto/Axiom-Dense-380M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use user-anto/Axiom-Dense-380M-Instruct with Docker Model Runner:
```
docker model run hf.co/user-anto/Axiom-Dense-380M-Instruct
```

user-anto commited on May 29

Commit

b3318dd

verified ·

1 Parent(s): 00b537b

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -2,7 +2,7 @@
 library_name: transformers
 license: apache-2.0
 datasets:
-- HuggingFaceTB/smoltalk
 language:
 - en
 pipeline_tag: text-generation
@@ -75,7 +75,7 @@ This model preserves the same dense Transformer stack as the base model, but uti
 ## Training Data
-- Source dataset: `HuggingFaceTB/smoltalk`
 - Local dataset path during training: `data/smol-smoltalk`
 - SFT targets: Computes loss only on assistant response tokens, masking out prompt and user tokens.
 - Total training tokens: 204,802,175 (~0.205B tokens)

 library_name: transformers
 license: apache-2.0
 datasets:
+- HuggingFaceTB/smol-smoltalk
 language:
 - en
 pipeline_tag: text-generation
 ## Training Data
+- Source dataset: `HuggingFaceTB/smol-smoltalk`
 - Local dataset path during training: `data/smol-smoltalk`
 - SFT targets: Computes loss only on assistant response tokens, masking out prompt and user tokens.
 - Total training tokens: 204,802,175 (~0.205B tokens)