Instructions to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Use pre-built binary

# 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 noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Build from source code

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 noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Use Docker

docker model run hf.co/noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "noctrex/Olmo-3-7B-Instruct-abliterated-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "noctrex/Olmo-3-7B-Instruct-abliterated-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Ollama
How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with Ollama:
```
ollama run hf.co/noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M
```
Unsloth Desktop

How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with Docker Model Runner:
```
docker model run hf.co/noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M
```

Lemonade

How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Olmo-3-7B-Instruct-abliterated-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use noctrex/Olmo-3-7B-Instruct-abliterated-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "noctrex/Olmo-3-7B-Instruct-abliterated-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

This is an abliterated version of Olmo-3-7B-Instruct, made using Heretic v1.0.1

The quantizations were created using an imatrix merged from combined_en_small and harmful.txt to leverage the abliterated nature of the model.

Performance

It already was less obstructive than other models, at 28% against 80+% of other models, but it can always be improved!

Metric	This model	Original model
KL divergence	0.0	0 (by definition)
Refusals	6/100	28/100

It's impressive that the KL divergence remained at 0.

Analysis against the original model:

Detailed Analysis:

Total Tensors: 355
Tensors with Diffs: 32 (9.0%)
Average % Diff: 3.73%
Median % Diff: 0.00%
Min/Max % Diff: 0.00% / 44.48%
Std Dev % Diff: 11.88%
Skewness % Diff: 2.88
Avg L2 Norm: 85225.25
Tensors with >5% diff: 32
Top differences: blk.21.attn_output.weight ((4096, 8192), L2: 659830.15): 44.48% blk.25.ffn_down.weight ((4096, 22016), L2: 1075726.18): 43.86% blk.20.attn_output.weight ((4096, 8192), L2: 655471.58): 43.76% blk.22.attn_output.weight ((4096, 8192), L2: 655063.13): 43.67% blk.24.ffn_down.weight ((4096, 22016), L2: 1070648.90): 43.38%

File Comparison: File 1: Avg Abs Value = 77.9757, Deviation Score = 0.0586 File 2: Avg Abs Value = 77.9732, Deviation Score = 0.0586 Positive Diffs (File 1 > File 2): 32, Negative Diffs (File 2 > File 1): 0

BibTeX entry and citation info

@misc{heretic,
  author = {Weidmann, Philipp Emanuel},
  title = {Heretic: Fully automatic censorship removal for language models},
  year = {2025},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/p-e-w/heretic}}
}

Original model card:

Model Details

Model Card for Olmo 3 7B Instruct

We introduce Olmo 3, a new family of 7B and 32B models both Instruct and Think variants. Long chain-of-thought thinking improves reasoning tasks like math and coding.

Olmo is a series of Open language models designed to enable the science of language models. These models are pre-trained on the Dolma 3 dataset and post-trained on the Dolci datasets. We are releasing all code, checkpoints, logs (coming soon), and associated training details.

The core models released in this batch include the following:

Stage	Olmo 3 7B Think	Olmo 3 32B Think	Olmo 3 7B Instruct
Base Model	Olmo-3-7B	Olmo-3-32B	Olmo-3-7B
SFT	Olmo-3-7B-Think-SFT	Olmo-3-32B-Think-SFT	Olmo-3-7B-Instruct-SFT
DPO	Olmo-3-7B-Think-DPO	Olmo-3-32B-Think-DPO	Olmo-3-7B-Instruct-DPO
Final Models (RLVR)	Olmo-3-7B-Think	Olmo-3-32B-Think	Olmo-3-7B-Instruct

Installation

Olmo 3 is supported in transformers 4.57.0 or higher:

pip install transformers>=4.57.0

Inference

You can use OLMo with the standard HuggingFace transformers library:

from transformers import AutoModelForCausalLM, AutoTokenizer
olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct")
tokenizer = AutoTokenizer.from_pretrained("allenai/Olmo-3-7B-Instruct")
message = ["Who would win in a fight - a dinosaur or a cow named Moo Moo?"]
inputs = tokenizer(message, return_tensors='pt', return_token_type_ids=False)
# optional verifying cuda
# inputs = {k: v.to('cuda') for k,v in inputs.items()}
# olmo = olmo.to('cuda')
response = olmo.generate(**inputs, max_new_tokens=100, do_sample=True, top_k=50, top_p=0.95)
print(tokenizer.batch_decode(response, skip_special_tokens=True)[0])
>> 'This is a fun and imaginative question! Let’s break it down...'

For faster performance, you can quantize the model using the following method:

AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct", 
    torch_dtype=torch.float16, 
    load_in_8bit=True)  # Requires bitsandbytes

The quantized model is more sensitive to data types and CUDA operations. To avoid potential issues, it's recommended to pass the inputs directly to CUDA using:

inputs.input_ids.to('cuda')

We have released checkpoints for these models. For post-training, the naming convention is step_XXXX.

To load a specific model revision with HuggingFace, simply add the argument revision:

olmo = AutoModelForCausalLM.from_pretrained("allenai/Olmo-3-7B-Instruct", revision="step_300")

Or, you can access all the revisions for the models via the following code snippet:

from huggingface_hub import list_repo_refs
out = list_repo_refs("allenai/Olmo-3-7B-Instruct")
branches = [b.name for b in out.branches]

Chat template

Default System Message

The default system prompt for this model is:

<|im_start|>system
You are a helpful function-calling AI assistant. 
You do not currently have access to any functions. <functions></functions><|im_end|>

Chat Format

The chat template for this model is formatted as:

<|im_start|>system
You are a helpful function-calling AI assistant. 
You do not currently have access to any functions. <functions></functions><|im_end|>
<|im_start|>user
Who would win in a fight - a dinosaur or a cow named Moo Moo?<|im_end|>
<|im_start|>assistant
This is a fun and imaginative question! Let’s break it down...
Moo Moo the cow would certinaly win.
<|endoftext|>

Model Description

Developed by: Allen Institute for AI (Ai2)
Model type: a Transformer style autoregressive language model.
Language(s) (NLP): English
License: This model is licensed under Apache 2.0. It is intended for research and educational use in accordance with Ai2's Responsible Use Guidelines.
Contact: Technical inquiries: olmo@allenai.org. Press: press@allenai.org
Date cutoff: Dec. 2024.

Model Sources

Project Page: https://allenai.org/olmo
Repositories:
- Open-Instruct for DPO and RLVR: https://github.com/allenai/open-instruct
- OLMo-Core for pre-training and SFT: https://github.com/allenai/OLMo-core
- OLMo-Eval for evaluation: https://github.com/allenai/OLMo-Eval
Paper: [TBD]

Evaluation

Skill	Benchmark	Olmo 3 Instruct 7B SFT	Olmo 3 Instruct 7B DPO	Olmo3 Instruct 7B	Qwen 3 8B (no reasoning)	Qwen 3 VL 8B Instruct	Qwen 2.5 7B	Olmo 2 7B Instruct	Apertus 8B Instruct	Granite 3.3 8B Instruct
Math	MATH	65.1	79.6	87.3	82.3	91.6	71.0	30.1	21.9	67.3
	AIME 2024	6.7	23.5	44.3	26.2	55.1	11.3	1.3	0.5	7.3
	AIME 2025	7.2	20.4	32.5	21.7	43.3	6.3	0.4	0.2	6.3
	OMEGA	14.4	22.8	28.9	20.5	32.3	13.7	5.2	5.0	10.7
Reasoning	BigBenchHard	51.0	69.3	71.2	73.7	85.6	68.8	43.8	42.2	61.2
	ZebraLogic	18.0	28.4	32.9	25.4	64.3	10.7	5.3	5.3	17.6
	AGI Eval English	59.2	64.0	64.4	76.0	84.5	69.8	56.1	50.8	64.0
Coding	HumanEvalPlus	69.8	72.9	77.2	79.8	82.9	74.9	25.8	34.4	64.0
	MBPP+	56.5	55.9	60.2	64.4	66.3	62.6	40.7	42.1	54.0
	LiveCodeBench v3	20.0	18.8	29.5	53.2	55.9	34.5	7.2	7.8	11.5
IF	IFEval	81.7	82.0	85.6	86.3	87.8	73.4	72.2	71.4	77.5
	IFBench	27.4	29.3	32.3	29.3	34.0	28.4	26.7	22.1	22.3
Knowledge	MMLU	67.1	69.1	69.1	80.4	83.6	77.2	61.6	62.7	63.5
QA	PopQA	16.5	20.7	14.1	20.4	26.5	21.5	25.5	25.5	28.9
	GPQA	30.0	37.9	40.4	44.6	51.1	35.6	31.3	28.8	33.0
Chat	AlpacaEval 2 LC	21.8	43.3	40.9	49.8	73.5	23.0	18.3	8.1	28.6
Tool Use	SimpleQA	74.2	79.8	79.3	79.0	90.3	78.0	–	–	–
	LitQA2	38.0	43.3	38.2	39.6	30.7	29.8	–	–	–
	BFCL	48.9	49.6	49.8	60.2	66.2	55.8	–	–	–
Safety	Safety	89.2	90.2	87.3	78.0	80.2	73.4	93.1	72.2	73.7

Model Details

Stage 1: SFT

supervised fine-tuning on the Dolci-Think-SFT-7B dataset. This dataset consits of math, code, chat, and general knowledge queries.
Datasets: Dolci-Think-SFT-7B, Dolci-Instruct-SFT-7B

Stage 2:DPO

direct preference optimization on the Dolci-Think-DPO-7B dataset. This dataset consits of math, code, chat, and general knowledge queries.
Datasets: Dolci-Think-DPO-7B, Dolci-Instruct-DPO-7B

Stage 3: RLVR

reinforcement learning from verifiable rewards on the Dolci-Think-RL-7B dataset. This dataset consits of math, code, instruction-following, and general chat queries.
Datasets: Dolci-Think-RL-7B, Dolci-Instruct-RL-7B

Bias, Risks, and Limitations

Like any base language model or fine-tuned model without safety filtering, these models can easily be prompted by users to generate harmful and sensitive content. Such content may also be produced unintentionally, especially in cases involving bias, so we recommend that users consider the risks when applying this technology. Additionally, many statements from OLMo or any LLM are often inaccurate, so facts should be verified.