Instructions to use camgeodesic/olmo3-7b-instruct-only with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use camgeodesic/olmo3-7b-instruct-only with Transformers:

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

pipe = pipeline("text-generation", model="camgeodesic/olmo3-7b-instruct-only")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("camgeodesic/olmo3-7b-instruct-only")
model = AutoModelForCausalLM.from_pretrained("camgeodesic/olmo3-7b-instruct-only")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use camgeodesic/olmo3-7b-instruct-only with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "camgeodesic/olmo3-7b-instruct-only"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "camgeodesic/olmo3-7b-instruct-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/camgeodesic/olmo3-7b-instruct-only

SGLang

How to use camgeodesic/olmo3-7b-instruct-only 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 "camgeodesic/olmo3-7b-instruct-only" \
    --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": "camgeodesic/olmo3-7b-instruct-only",
		"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 "camgeodesic/olmo3-7b-instruct-only" \
        --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": "camgeodesic/olmo3-7b-instruct-only",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use camgeodesic/olmo3-7b-instruct-only with Docker Model Runner:
```
docker model run hf.co/camgeodesic/olmo3-7b-instruct-only
```

OLMo-3 7B Instruct-Only (GRPO)

Fine-tuned from allenai/OLMo-3-1025-7B using GRPO (Group Relative Policy Optimization) on instruction-following tasks.

Training Details

Base model: allenai/OLMo-3-1025-7B
Training method: GRPO with RL-Zero (no supervised warmup)
Dataset: allenai/Dolci-RLZero-IF-7B (IFEval instruction-following)
Config: if_valley_thinker — valley length penalty (512–4096 token sweet spot) + think token reward shaping
Chat template: OLMo thinker (prefills <think> tag for chain-of-thought reasoning)
Precision: bfloat16
Hardware: 2 nodes × 4 NVIDIA GH200 120GB GPUs (Isambard-AI)

Reward Components

Component	Description
IFEval verifiable reward	Binary per-constraint score for instruction-following
Valley length penalty	Penalizes responses <512 or >4096 tokens (coeff: -0.001)
Think tag reward	+0.125 for correct `</think>` closure
Think length penalty	-0.1 if thinking block <10 words

Performance (late-stage averages)

Metric	Value
IFEval correct rate	0.88
Training reward	6.36
Think word count	~886 words
Sequence length	~1353 tokens

Checkpoints

Each training checkpoint is available as a separate branch/revision:

main — step 3800 (latest)
step_600 through step_3600 — intermediate checkpoints (every 200 steps)

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load latest
model = AutoModelForCausalLM.from_pretrained("camgeodesic/olmo3-7b-instruct-only")

# Load specific checkpoint
model = AutoModelForCausalLM.from_pretrained("camgeodesic/olmo3-7b-instruct-only", revision="step_2000")

Downloads last month: 4

Safetensors

Model size

528k params

Tensor type

BF16

Model tree for camgeodesic/olmo3-7b-instruct-only

Finetunes

1 model