Total runs:
24.5K
Run Growth:
491
Growth Rate:
2.01%
Sponsored by
iMean AI Trip Planner
arcee-ai / AFM-4.5B-Preview
Model's Last Updated: September 18 2025
text-generation
Introduction of AFM-4.5B-Preview
Model Details of AFM-4.5B-Preview
These are the weights for the preview model hosted on TogetherAI between June 18th-July 28th. For the final release checkpoint optimized for retrieval, instruction following and assistant use cases please see AFM-4.5B
AFM-4.5B-Preview
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.
View our documentation here for more details: https://docs.arcee.ai/arcee-foundation-models/introduction-to-arcee-foundation-models
Model Details
- Model Architecture: ArceeForCausalLM
- Parameters: 4.5B
- Training Tokens:
- License: Arcee Model License (AML)
-
Recommended settings:
- temperature: 0.5
- top_k: 50
- top_p: 0.95
- repeat_penalty: 1.1
Benchmarks
*Qwen3 and SmolLM's reasoning approach causes their scores to vary wildly from suite to suite - but these are all scores on our internal harness with the same hyperparameters. Be sure to reference their reported scores. SmolLM just released its
bench
.
How to use with
transformers
You can use the model directly with the
transformers
library.
We recommend a lower temperature, around 0.5, for optimal performance.
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_id = "arcee-ai/AFM-4.5B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
messages = [
{"role": "user", "content": "Who are you?"},
]
input_ids = tokenizer.apply_chat_template(
messages,
add_generation_prompt=True,
return_tensors="pt"
).to(model.device)
outputs = model.generate(
input_ids,
max_new_tokens=256,
do_sample=True,
temperature=0.5,
top_k=50,
top_p=0.95
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
How to use with
vllm
Pending a PR merge: https://github.com/vllm-project/vllm/pull/21725
How to use with Together API
You can access this model directly via the Together Playground .
Python (Official Together SDK)
from together import Together
client = Together()
response = client.chat.completions.create(
model="arcee-ai/AFM-4.5B",
messages=[
{
"role": "user",
"content": "What are some fun things to do in New York?"
}
]
)
print(response.choices[0].message.content)
cURL
curl -X POST "https://api.together.xyz/v1/chat/completions" \
-H "Authorization: Bearer $TOGETHER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "arcee-ai/AFM-4.5B",
"messages": [
{
"role": "user",
"content": "What are some fun things to do in New York?"
}
]
}'
Quantization support
Support for llama.cpp is available, GGUF format quants are provided here:
https://huggingface.co/arcee-ai/AFM-4.5B-GGUF
License
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-Preview on huggingface.co
108
Total runs
3
24-hour runs
8
3-day runs
22
7-day runs
73
30-day runs
More Information About AFM-4.5B-Preview huggingface.co Model
Url of AFM-4.5B-Preview
AFM-4.5B-Preview huggingface.co Url
Provider of AFM-4.5B-Preview huggingface.co
Other API from arcee-ai
Updated:May 29 2026
Total runs:
10.0K
Run Growth:
9.3K
Growth Rate:
92.47%
Total runs:
4.3K
Run Growth:
-9.0K
Growth Rate:
-210.80%
Total runs:
4.3K
Run Growth:
-1.2K
Growth Rate:
-27.15%
Total runs:
2.6K
Run Growth:
2.5K
Growth Rate:
92.71%
Total runs:
2.3K
Run Growth:
1.3K
Growth Rate:
54.85%
Total runs:
1.8K
Run Growth:
1.5K
Growth Rate:
82.87%
Total runs:
1.7K
Run Growth:
889
Growth Rate:
51.00%
Total runs:
1.7K
Run Growth:
-860
Growth Rate:
-49.60%
Total runs:
1.5K
Run Growth:
1.5K
Growth Rate:
98.63%
Total runs:
1.5K
Run Growth:
422
Growth Rate:
28.73%
Total runs:
1.5K
Run Growth:
1.4K
Growth Rate:
96.05%
Total runs:
1.4K
Run Growth:
1.0K
Growth Rate:
76.91%
Total runs:
1.3K
Run Growth:
1.2K
Growth Rate:
90.25%
Total runs:
1.2K
Run Growth:
-106
Growth Rate:
-8.55%
Total runs:
1.0K
Run Growth:
-1.8K
Growth Rate:
-174.58%
Total runs:
1.0K
Run Growth:
129
Growth Rate:
12.89%
Total runs:
850
Run Growth:
0
Growth Rate:
0.00%
Total runs:
836
Run Growth:
-958
Growth Rate:
-114.59%
Total runs:
766
Run Growth:
-6.3K
Growth Rate:
-820.89%
Total runs:
614
Run Growth:
-4.4K
Growth Rate:
-715.15%
Total runs:
606
Run Growth:
-964
Growth Rate:
-159.08%
Total runs:
557
Run Growth:
239
Growth Rate:
43.61%
Total runs:
528
Run Growth:
-163
Growth Rate:
-30.87%
Total runs:
505
Run Growth:
201
Growth Rate:
39.80%
Total runs:
503
Run Growth:
382
Growth Rate:
75.94%
Total runs:
476
Run Growth:
457
Growth Rate:
96.01%
Total runs:
448
Run Growth:
107
Growth Rate:
23.88%
Total runs:
433
Run Growth:
402
Growth Rate:
92.84%
Total runs:
408
Run Growth:
0
Growth Rate:
0.00%
Total runs:
373
Run Growth:
138
Growth Rate:
37.00%
Total runs:
351
Run Growth:
351
Growth Rate:
100.00%
Total runs:
281
Run Growth:
0
Growth Rate:
0.00%
Total runs:
268
Run Growth:
204
Growth Rate:
76.69%
Total runs:
261
Run Growth:
-561
Growth Rate:
-214.94%
Total runs:
243
Run Growth:
-1.7K
Growth Rate:
-680.25%
Total runs:
211
Run Growth:
150
Growth Rate:
71.09%
Total runs:
182
Run Growth:
94
Growth Rate:
51.65%
Total runs:
176
Run Growth:
95
Growth Rate:
53.67%
Total runs:
165
Run Growth:
109
Growth Rate:
67.28%
Total runs:
158
Run Growth:
-1
Growth Rate:
-0.63%
Total runs:
148
Run Growth:
-99
Growth Rate:
-66.89%
Total runs:
134
Run Growth:
61
Growth Rate:
45.52%
Total runs:
129
Run Growth:
50
Growth Rate:
38.76%
Total runs:
127
Run Growth:
26
Growth Rate:
20.47%
Total runs:
122
Run Growth:
92
Growth Rate:
75.41%
Total runs:
110
Run Growth:
100
Growth Rate:
90.91%
Total runs:
108
Run Growth:
74
Growth Rate:
69.81%
Total runs:
107
Run Growth:
83
Growth Rate:
78.30%
Total runs:
105
Run Growth:
71
Growth Rate:
67.62%
Total runs:
103
Run Growth:
80
Growth Rate:
77.67%
Total runs:
103
Run Growth:
81
Growth Rate:
78.64%
Total runs:
101
Run Growth:
69
Growth Rate:
68.32%
Total runs:
101
Run Growth:
79
Growth Rate:
78.22%
Total runs:
99
Run Growth:
77
Growth Rate:
77.78%
Total runs:
99
Run Growth:
69
Growth Rate:
70.41%
Total runs:
97
Run Growth:
74
Growth Rate:
77.08%
Total runs:
97
Run Growth:
72
Growth Rate:
75.00%
Total runs:
96
Run Growth:
74
Growth Rate:
77.08%
Total runs:
96
Run Growth:
74
Growth Rate:
77.08%
Total runs:
94
Run Growth:
18
Growth Rate:
19.57%
Total runs:
93
Run Growth:
60
Growth Rate:
64.52%
Total runs:
93
Run Growth:
67
Growth Rate:
72.04%
Total runs:
93
Run Growth:
68
Growth Rate:
73.12%
Total runs:
92
Run Growth:
66
Growth Rate:
71.74%
Total runs:
92
Run Growth:
74
Growth Rate:
80.43%
Total runs:
92
Run Growth:
56
Growth Rate:
60.87%
Total runs:
92
Run Growth:
33
Growth Rate:
35.87%
Total runs:
92
Run Growth:
70
Growth Rate:
76.09%
Total runs:
91
Run Growth:
63
Growth Rate:
69.23%
Total runs:
91
Run Growth:
75
Growth Rate:
83.33%