Instructions to use ThingAI/Dwarf-15M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThingAI/Dwarf-15M with Transformers:

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

pipe = pipeline("text-generation", model="ThingAI/Dwarf-15M", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("ThingAI/Dwarf-15M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ThingAI/Dwarf-15M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThingAI/Dwarf-15M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThingAI/Dwarf-15M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThingAI/Dwarf-15M

SGLang

How to use ThingAI/Dwarf-15M 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 "ThingAI/Dwarf-15M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThingAI/Dwarf-15M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "ThingAI/Dwarf-15M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThingAI/Dwarf-15M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ThingAI/Dwarf-15M with Docker Model Runner:
```
docker model run hf.co/ThingAI/Dwarf-15M
```

ThingsAI commited on Jun 21

Commit

5c383d8

verified ·

1 Parent(s): 441dc44

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -12,11 +12,11 @@ tags:
 - small-language-model
 pipeline_tag: text-generation
 model-index:
-- name: Dwarf-15M-Instruct
   results: []
 ---
-# Dwarf-15M-Instruct
 A **15.54M parameter** shell/bash specialist language model that translates natural language into Linux commands.
@@ -25,8 +25,8 @@ A **15.54M parameter** shell/bash specialist language model that translates natu
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("ThingAI/Dwarf-15M-Instruct", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("ThingAI/Dwarf-15M-Instruct", trust_remote_code=True)
 prompt = "<|user|>\nFind all Python files modified in the last 3 days\n<|end|>\n<|assistant|>\n"
 inputs = tokenizer(prompt, return_tensors="pt")
@@ -79,7 +79,7 @@ Dwarf-15M takes natural language descriptions of tasks and produces the correspo
 - English: helpful-instructions, FineWeb — 10.3%
 - CoT: Magpie-Reasoning — 1.1%
-**SFT:** 557 curated Linux command pairs, 5 epochs, lr=4e-5. Training time: 19 seconds.
 **Tokenizer:** [DwarfGoToken](https://huggingface.co/ThingAI/DwarfGoToken) — 8,202 token BPE with syntax-aware pre-tokenization for shell operators (2>&1, &&, >>).
@@ -122,7 +122,7 @@ Apache 2.0
 ```bibtex
 @misc{dwarf15m2026,
-  title={Dwarf-15M-Instruct: A Shell Specialist Language Model},
   author={ThingsAI},
   year={2026},
   url={https://huggingface.co/ThingAI/Dwarf-15M-Instruct}

 - small-language-model
 pipeline_tag: text-generation
 model-index:
+- name: Dwarf-15M
   results: []
 ---
+# Dwarf-15M
 A **15.54M parameter** shell/bash specialist language model that translates natural language into Linux commands.
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("ThingAI/Dwarf-15M", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("ThingAI/Dwarf-15M", trust_remote_code=True)
 prompt = "<|user|>\nFind all Python files modified in the last 3 days\n<|end|>\n<|assistant|>\n"
 inputs = tokenizer(prompt, return_tensors="pt")
 - English: helpful-instructions, FineWeb — 10.3%
 - CoT: Magpie-Reasoning — 1.1%
+**SFT:** 900 curated Linux command pairs, 5 epochs, lr=4e-5. Training time: 19 seconds.
 **Tokenizer:** [DwarfGoToken](https://huggingface.co/ThingAI/DwarfGoToken) — 8,202 token BPE with syntax-aware pre-tokenization for shell operators (2>&1, &&, >>).
 ```bibtex
 @misc{dwarf15m2026,
+  title={Dwarf-15M: A Shell Specialist Language Model},
   author={ThingsAI},
   year={2026},
   url={https://huggingface.co/ThingAI/Dwarf-15M-Instruct}