Instructions to use mjbommar/linux-as-a-model-32M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mjbommar/linux-as-a-model-32M with Transformers:

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

pipe = pipeline("text-generation", model="mjbommar/linux-as-a-model-32M")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mjbommar/linux-as-a-model-32M")
model = AutoModelForCausalLM.from_pretrained("mjbommar/linux-as-a-model-32M", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mjbommar/linux-as-a-model-32M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mjbommar/linux-as-a-model-32M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mjbommar/linux-as-a-model-32M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mjbommar/linux-as-a-model-32M

SGLang

How to use mjbommar/linux-as-a-model-32M 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 "mjbommar/linux-as-a-model-32M" \
    --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": "mjbommar/linux-as-a-model-32M",
		"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 "mjbommar/linux-as-a-model-32M" \
        --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": "mjbommar/linux-as-a-model-32M",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mjbommar/linux-as-a-model-32M with Docker Model Runner:
```
docker model run hf.co/mjbommar/linux-as-a-model-32M
```

mjbommar commited on Jun 17, 2024

Commit

d9ecdaf

verified ·

1 Parent(s): 9edbf84

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -17

README.md CHANGED Viewed

@@ -46,24 +46,19 @@ emits copies of Linux 1.0 source code.  For example, using the HuggingFace hub c
 ```python
 >>> from transformers import pipeline
->>> p = pipeline('text-generation', 'mjbommar/linux-as-a-model-5M')
 >>> print(p('', max_new_tokens=256, do_sample=True, temperature=0.2)[0]['generated_text'])
- linux/drivers/net/3c503.c /* 3c503.c: A shared-memory NS8390 ethernet driver for linux. */
-/*
- Written 1992,1993 by Donald Becker.
- Copyright 1993 United States Government as represented by the
- Director, National Security Agency. This software may be used and
- distributed according to the terms of the GNU Public License,
- incorporated herein by reference.
- This driver should work with the 3c503 and 3c503/16. It should be used
- in shared memory mode for best performance, although it may also work
- in programmed-I/O mode.
- The Author may be reached as becker@super.org or
- C/O Supercomputing Research Ctr., 17100 Science Dr., Bowie MD 20715
-*/
 ```

 ```python
 >>> from transformers import pipeline
+>>> p = pipeline('text-generation', 'mjbommar/linux-as-a-model-32M')
 >>> print(p('', max_new_tokens=256, do_sample=True, temperature=0.2)[0]['generated_text'])
+ linux/drivers/FPU-emu/reg_u_div.S.file "reg_u_div.S"
+/*---------------------------------------------------------------------------+
+ | reg_u_div.S |
+ | |
+ | Core division routines |
+ | |
+ | Copyright (C) 1992,1993 |
+ | W. Metzenthen, 22 Parker St, Ormond, Vic 3163, |
+ | Australia. E-mail billm@vaxc.cc.monash.edu.au |
+ | |
+ |
 ```