Instructions to use CollectionStudio/AFM-4.5B-Base-Pre-Anneal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CollectionStudio/AFM-4.5B-Base-Pre-Anneal with Transformers:

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

pipe = pipeline("text-generation", model="CollectionStudio/AFM-4.5B-Base-Pre-Anneal")

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

tokenizer = AutoTokenizer.from_pretrained("CollectionStudio/AFM-4.5B-Base-Pre-Anneal")
model = AutoModelForCausalLM.from_pretrained("CollectionStudio/AFM-4.5B-Base-Pre-Anneal", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CollectionStudio/AFM-4.5B-Base-Pre-Anneal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CollectionStudio/AFM-4.5B-Base-Pre-Anneal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CollectionStudio/AFM-4.5B-Base-Pre-Anneal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CollectionStudio/AFM-4.5B-Base-Pre-Anneal

SGLang

How to use CollectionStudio/AFM-4.5B-Base-Pre-Anneal 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 "CollectionStudio/AFM-4.5B-Base-Pre-Anneal" \
    --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": "CollectionStudio/AFM-4.5B-Base-Pre-Anneal",
		"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 "CollectionStudio/AFM-4.5B-Base-Pre-Anneal" \
        --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": "CollectionStudio/AFM-4.5B-Base-Pre-Anneal",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CollectionStudio/AFM-4.5B-Base-Pre-Anneal with Docker Model Runner:
```
docker model run hf.co/CollectionStudio/AFM-4.5B-Base-Pre-Anneal
```

AFM-4.5B-Base-Pre-Anneal / README.md

CollectionStudio

sapiosaturn

Duplicate from arcee-ai/AFM-4.5B-Base-Pre-Anneal

0afaacc 4 days ago

preview code

Raw History Blame Contribute Delete

3.41 kB

	---
	license: apache-2.0
	language:
	- en
	- es
	- fr
	- de
	- it
	- pt
	- ru
	- ar
	- hi
	- ko
	- zh
	library_name: transformers
	extra_gated_prompt: Company name is optional, please put NA if you would prefer not to share it.
	---

	<div align="center">
	<picture>
	<img src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/Lj9YVLIKKdImV_jID0A1g.png" width="25%" alt="Arcee AFM 4.5B">
	</picture>
	</div>

	# AFM-4.5B-Base-Pre-Anneal

	AFM-4.5B-Base-Pre-Anneal is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge. The base model was trained on a dataset of 6.5 trillion tokens of general pretraining data. We use a modified version of [TorchTitan](https://arxiv.org/abs/2410.06511) for pretraining.

	The development of AFM-4.5B prioritized data quality as a fundamental requirement for achieving robust model performance. We collaborated with DatologyAI, a company specializing in large-scale data curation. DatologyAI's curation pipeline integrates a suite of proprietary algorithms—model-based quality filtering, embedding-based curation, target distribution-matching, source mixing, and synthetic data. Their expertise enabled the creation of a curated dataset tailored to support strong real-world performance.

	The model architecture follows a standard transformer decoder-only design based on Vaswani et al., incorporating several key modifications for enhanced performance and efficiency. Notable architectural features include grouped query attention for improved inference efficiency and ReLU^2 activation functions instead of SwiGLU to enable sparsification while maintaining or exceeding performance benchmarks.

	The model available in this repo is the base model before it was annealed with math and code and before merging and context extension.

	***

	<div align="center">
	<picture>
	<img src="https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/sSVjGNHfrJKmQ6w8I18ek.png" style="background-color:ghostwhite;padding:5px;" width="17%" alt="Powered by Datology">
	</picture>
	</div>

	## Model Details

	* Model Architecture: ArceeForCausalLM
	* Parameters: 4.5B
	* Training Tokens: 6.5T - this model is pre-annealing with math and code and uses only the general dataset.
	* License: [Apache-2.0](https://huggingface.co/arcee-ai/AFM-4.5B-Base#license)

	***

	## Benchmarks

	![image/png](https://cdn-uploads.huggingface.co/production/uploads/6435718aaaef013d1aec3b8b/rxUKBWNf2piJwdKhKC3tZ.png)

	## How to use with `transformers`

	You can use the model directly with the `transformers` library.

	```python
	from transformers import AutoTokenizer, AutoModelForCausalLM
	import torch

	model_id = "arcee-ai/AFM-4.5B-Base-Pre-Anneal"
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	torch_dtype=torch.bfloat16,
	device_map="auto"
	)

	prompt = "Once upon a time "
	input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)

	# Generate text
	outputs = model.generate(
	input_ids,
	max_new_tokens=100,
	do_sample=True,
	temperature=0.7,
	top_p=0.95
	)

	generated_text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
	print(generated_text)
	```

	## License

	AFM-4.5B is released under the Apache-2.0 license.