OLMo 2 32B

pip install -U transformers

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

pipe = pipeline("text-generation", model="allenai/OLMo-2-0325-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

pip install -U transformers

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("allenai/OLMo-2-0325-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained("allenai/OLMo-2-0325-32B-Instruct", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

curl -LsSf https://llama.app/install.sh | sh

# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

# Run inference directly in the terminal:
llama cli -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

winget install llama.cpp

# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

# Run inference directly in the terminal:
llama cli -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases

# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

# Run inference directly in the terminal:
./llama-cli -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli

# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

docker model run hf.co/unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

ollama run hf.co/unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

npx -y node-llama-cpp chat hf:unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

npx -y node-llama-cpp inspect estimate hf:unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

docker model run hf.co/unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

curl https://localai.io/install.sh | sh

# Load and run the model:
local-ai run huggingface://unsloth/OLMo-2-0325-32B-Instruct-GGUF/{{GGUF_FILE}}

# Pull the image:
docker pull localai/localai:latest-cpu

# Load and run the model:
docker run -p 8080:8080 --name localai -v $PWD/models:/build/models localai/localai:latest-cpu huggingface://unsloth/OLMo-2-0325-32B-Instruct-GGUF/{{GGUF_FILE}}

# Download Lemonade from https://lemonade-server.ai/

lemonade pull unsloth/OLMo-2-0325-32B-Instruct-GGUF:Q4_K_M

lemonade run user.OLMo-2-0325-32B-Instruct-GGUF-Q4_K_M

lemonade list