AFM-4.5B 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 8 trillion tokens, comprising 6.5 trillion tokens of general pretraining data followed by 1.5 trillion tokens of midtraining data with enhanced focus on mathematical reasoning and code generation. Following pretraining, the model underwent supervised fine-tuning on high-quality instruction datasets. The instruction-tuned model was further refined through reinforcement learning on verifiable rewards as well as for human preference. We use a modified version of
TorchTitan
for pretraining,
Axolotl
for supervised fine-tuning, and a modified version of
Verifiers
for reinforcement learning.
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 instruct model following supervised fine-tuning and reinforcement learning.
AFM-4.5B is released under the
Arcee Model License
. If your company makes less than $1.75 million in annual revenue, you’re free to use the model for commercial purposes, as long as you’re not providing the weights to a company above that threshold. If your product or application using AFM-4.5B is sold to a larger company, that’s fine—as long as they don’t receive or run the weights directly.
We want as many developers, researchers, and builders as possible to benefit from AFM-4.5B. At the same time, this license ensures that we can continue to develop and support the model for the community.
Runs of arcee-ai AFM-4.5B-GGUF on huggingface.co
366
Total runs
1
24-hour runs
-9
3-day runs
-69
7-day runs
21
30-day runs
More Information About AFM-4.5B-GGUF huggingface.co Model
AFM-4.5B-GGUF huggingface.co is an AI model on huggingface.co that provides AFM-4.5B-GGUF's model effect (), which can be used instantly with this arcee-ai AFM-4.5B-GGUF model. huggingface.co supports a free trial of the AFM-4.5B-GGUF model, and also provides paid use of the AFM-4.5B-GGUF. Support call AFM-4.5B-GGUF model through api, including Node.js, Python, http.
AFM-4.5B-GGUF huggingface.co is an online trial and call api platform, which integrates AFM-4.5B-GGUF's modeling effects, including api services, and provides a free online trial of AFM-4.5B-GGUF, you can try AFM-4.5B-GGUF online for free by clicking the link below.
arcee-ai AFM-4.5B-GGUF online free url in huggingface.co:
AFM-4.5B-GGUF is an open source model from GitHub that offers a free installation service, and any user can find AFM-4.5B-GGUF on GitHub to install. At the same time, huggingface.co provides the effect of AFM-4.5B-GGUF install, users can directly use AFM-4.5B-GGUF installed effect in huggingface.co for debugging and trial. It also supports api for free installation.