Instructions to use jgalego/olmputer-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jgalego/olmputer-tiny with Transformers:

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

pipe = pipeline("text-generation", model="jgalego/olmputer-tiny")

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

tokenizer = AutoTokenizer.from_pretrained("jgalego/olmputer-tiny")
model = AutoModelForCausalLM.from_pretrained("jgalego/olmputer-tiny", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jgalego/olmputer-tiny with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jgalego/olmputer-tiny

SGLang

How to use jgalego/olmputer-tiny 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 "jgalego/olmputer-tiny" \
    --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": "jgalego/olmputer-tiny",
		"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 "jgalego/olmputer-tiny" \
        --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": "jgalego/olmputer-tiny",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jgalego/olmputer-tiny with Docker Model Runner:
```
docker model run hf.co/jgalego/olmputer-tiny
```

olmputer-tiny / example.py

jgalego

Upload folder using huggingface_hub

a080b45 verified 12 days ago

Raw History Blame Contribute Delete

1.61 kB

# /// script
# requires-python = ">=3.12"
# dependencies = [
#     "chipformer @ https://github.com/JGalego/olmputer/archive/98639dff4c84a18542e3ca12a286a4df563b3a27.tar.gz#subdirectory=experimental/riscv",  # pylint: disable=line-too-long
#     "huggingface_hub",
#     "torch==2.14.1",
#     "transformers==5.19.0",
# ]
# ///
"""Run fibonacci(25) on olmputer-tiny, the RISC-V computer in its weights.
The program's code and registers are written into the model's Gated DeltaNet states, and greedy
generate then runs the CPU: each token it generates is the next token of the execution trace. The
program ends with mv a0, t0 (the result), li a7, 93 and the exit ecall, so the result is the
second-to-last value record the model wrote.
"""

import torch
from chipformer.q35.ir import OLMO
from chipformer.rv import core, firmware, ref, spec
from chipformer.rv.programs import program
from transformers import OlmoHybridForCausalLM

DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
MODEL = OlmoHybridForCausalLM.from_pretrained("jgalego/olmputer-tiny", dtype=torch.bfloat16)
MODEL = MODEL.to(DEVICE).eval()
CIRCUIT = core.build(OLMO)  # the CPU as a circuit: it writes the program into the model's cache

TRACE = firmware.run(MODEL, CIRCUIT, ref.Machine.from_program(program("fib")))
VALUES = [spec.decode_value(TRACE[:i + 1]) for i, t in enumerate(TRACE)
          if spec.family(t)[0] in ("F0", "F1", "F2")]
print("fibonacci(25) =", VALUES[-2])
print(f"{len(TRACE)} trace tokens on {DEVICE}, identical to the reference machine:",
      TRACE == ref.Machine.from_program(program("fib")).run()[1:])

	# /// script
	# requires-python = ">=3.12"
	# dependencies = [
	# "chipformer @ https://github.com/JGalego/olmputer/archive/98639dff4c84a18542e3ca12a286a4df563b3a27.tar.gz#subdirectory=experimental/riscv", # pylint: disable=line-too-long
	# "huggingface_hub",
	# "torch==2.14.1",
	# "transformers==5.19.0",
	# ]
	# ///
	"""Run fibonacci(25) on olmputer-tiny, the RISC-V computer in its weights.

	The program's code and registers are written into the model's Gated DeltaNet states, and greedy
	generate then runs the CPU: each token it generates is the next token of the execution trace. The
	program ends with mv a0, t0 (the result), li a7, 93 and the exit ecall, so the result is the
	second-to-last value record the model wrote.
	"""

	import torch
	from chipformer.q35.ir import OLMO
	from chipformer.rv import core, firmware, ref, spec
	from chipformer.rv.programs import program
	from transformers import OlmoHybridForCausalLM

	DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
	MODEL = OlmoHybridForCausalLM.from_pretrained("jgalego/olmputer-tiny", dtype=torch.bfloat16)
	MODEL = MODEL.to(DEVICE).eval()
	CIRCUIT = core.build(OLMO) # the CPU as a circuit: it writes the program into the model's cache

	TRACE = firmware.run(MODEL, CIRCUIT, ref.Machine.from_program(program("fib")))
	VALUES = [spec.decode_value(TRACE[:i + 1]) for i, t in enumerate(TRACE)
	if spec.family(t)[0] in ("F0", "F1", "F2")]
	print("fibonacci(25) =", VALUES[-2])
	print(f"{len(TRACE)} trace tokens on {DEVICE}, identical to the reference machine:",
	TRACE == ref.Machine.from_program(program("fib")).run()[1:])