Sponsored by
APIMart
arcee-ai / Virtuoso-Medium-v2-GGUF
Model's Last Updated: January 30 2025
Introduction of Virtuoso-Medium-v2-GGUF
Model Details of Virtuoso-Medium-v2-GGUF
Virtuoso-Medium-v2 (32B) is our next-generation, 32-billion-parameter language model that builds upon the original Virtuoso-Medium architecture. This version is distilled from Deepseek-v3, leveraging an expanded dataset of 5B+ tokens worth of logits. It achieves higher benchmark scores than our previous release (including surpassing Arcee-Nova 2024 in certain tasks).
Model Details
- Architecture Base: Qwen-2.5-32B
- Parameter Count: 32B
-
Tokenizer:
- Initially integrated with Deepseek-v3 tokenizer for logit extraction.
- Final alignment uses the Qwen tokenizer, using specialized “tokenizer surgery” for cross-architecture compatibility.
-
Distillation Data:
- ~1.1B tokens/logits from Deepseek-v3’s training data.
- Logit-level distillation using a proprietary “fusion merging” approach afterwards for maximum fidelity.
- License: Apache-2.0
Background on Deepseek Distillation
Deepseek-v3 serves as the teacher model, from which we capture logits across billions of tokens. Rather than standard supervised fine-tuning, we apply a full logit-level replication. This ensures more precise transference of knowledge, including advanced reasoning in:
- Technical and scientific queries
- Complex code generation
- Mathematical problem-solving
Intended Use Cases
- Advanced Chatbots & Virtual Assistants
- Enterprise Data Analysis & Workflow Automation
- Research Simulations & Natural Language Understanding
- Educational Tools for STEM Fields
Evaluations
How to Use
Below is a sample code snippet using
transformers
:
from transformers import AutoTokenizer, AutoModelForCausalLM
model_name = "arcee-ai/virtuoso-medium-v2-32b"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)
prompt = "Provide a concise summary of quantum entanglement."
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=150)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Training & Fine-Tuning
- Initial Training: Began with Qwen-32B, calibrated for large-scale text ingestion.
-
Distillation & Merging:
- Trained on ~1.1B tokens worth of Deepseek-v3 logits.
- Employed “fusion merging” to retain as much teacher expertise as possible.
- Final step included DPO to improve alignment and reduce model hallucinations.
- Continuous Development: Additional R1 distillations are in progress to further enhance performance and specialization.
Performance
Thanks to a larger parameter count and a richer training corpus, Virtuoso-Medium-v2 delivers high scores across multiple benchmarks (BBH, MMLU-PRO, MATH, etc.). It frequently surpasses other 30B+ models and even some 70B+ architectures in specific tasks.
Limitations
- Context Length: 128k Tokens
- Knowledge Cut-off: Training data may not reflect the latest events or developments, leading to gaps in current knowledge beyond June 2024.
Ethical Considerations
- Content Generation Risks: Like any language model, Virtuoso-Medium-v2 can potentially generate harmful or biased content if prompted in certain ways.
License
Virtuoso-Medium-v2 (32B) is released under the Apache-2.0 License . You are free to use, modify, and distribute this model in both commercial and non-commercial applications, subject to the terms and conditions of the license.
If you have questions or would like to share your experiences using these models, please connect with us on social media. We’re excited to see what you build—and how these models help you innovate!
Runs of arcee-ai Virtuoso-Medium-v2-GGUF on huggingface.co
1.5K
Total runs
-1.0K
24-hour runs
-1.1K
3-day runs
-1.4K
7-day runs
-188
30-day runs
More Information About Virtuoso-Medium-v2-GGUF huggingface.co Model
Url of Virtuoso-Medium-v2-GGUF
Virtuoso-Medium-v2-GGUF huggingface.co Url
Provider of Virtuoso-Medium-v2-GGUF huggingface.co
Other API from arcee-ai
Total runs:
14.3K
Run Growth:
14.2K
Growth Rate:
99.11%
Total runs:
5.6K
Run Growth:
-752
Growth Rate:
-13.47%
Total runs:
3.4K
Run Growth:
-757
Growth Rate:
-21.63%
Total runs:
2.5K
Run Growth:
1.2K
Growth Rate:
48.53%
Total runs:
2.3K
Run Growth:
-925
Growth Rate:
-39.70%
Total runs:
1.9K
Run Growth:
1.1K
Growth Rate:
55.61%
Total runs:
1.8K
Run Growth:
1.5K
Growth Rate:
82.87%
Total runs:
1.7K
Run Growth:
-860
Growth Rate:
-49.60%
Total runs:
1.7K
Run Growth:
1.0K
Growth Rate:
63.04%
Total runs:
1.7K
Run Growth:
-3.2K
Growth Rate:
-191.35%
Total runs:
1.6K
Run Growth:
-221
Growth Rate:
-14.38%
Total runs:
1.5K
Run Growth:
1.5K
Growth Rate:
98.63%
Total runs:
1.2K
Run Growth:
-106
Growth Rate:
-8.55%
Total runs:
1.1K
Run Growth:
-302
Growth Rate:
-27.23%
Total runs:
1.0K
Run Growth:
-6
Growth Rate:
-0.58%
Total runs:
1.0K
Run Growth:
633
Growth Rate:
62.36%
Total runs:
1.0K
Run Growth:
-1.8K
Growth Rate:
-174.58%
Total runs:
1.0K
Run Growth:
240
Growth Rate:
22.02%
Total runs:
885
Run Growth:
-132
Growth Rate:
-15.10%
Total runs:
882
Run Growth:
-298
Growth Rate:
-32.96%
Total runs:
850
Run Growth:
0
Growth Rate:
0.00%
Total runs:
766
Run Growth:
-6.3K
Growth Rate:
-820.89%
Total runs:
680
Run Growth:
406
Growth Rate:
60.33%
Total runs:
614
Run Growth:
-4.4K
Growth Rate:
-715.15%
Total runs:
590
Run Growth:
-13
Growth Rate:
-2.20%
Total runs:
587
Run Growth:
-847
Growth Rate:
-143.80%
Total runs:
563
Run Growth:
231
Growth Rate:
38.06%
Total runs:
505
Run Growth:
201
Growth Rate:
39.80%
Total runs:
491
Run Growth:
169
Growth Rate:
34.99%
Total runs:
448
Run Growth:
107
Growth Rate:
23.88%
Total runs:
410
Run Growth:
175
Growth Rate:
42.68%
Total runs:
408
Run Growth:
0
Growth Rate:
0.00%
Total runs:
365
Run Growth:
-460
Growth Rate:
-123.99%
Total runs:
351
Run Growth:
351
Growth Rate:
100.00%
Total runs:
288
Run Growth:
125
Growth Rate:
44.48%
Total runs:
288
Run Growth:
179
Growth Rate:
63.25%
Total runs:
281
Run Growth:
0
Growth Rate:
0.00%
Total runs:
243
Run Growth:
-1.7K
Growth Rate:
-680.25%
Total runs:
225
Run Growth:
-40
Growth Rate:
-18.52%
Total runs:
218
Run Growth:
-143
Growth Rate:
-63.56%
Total runs:
187
Run Growth:
65
Growth Rate:
35.52%
Total runs:
165
Run Growth:
73
Growth Rate:
44.79%
Total runs:
158
Run Growth:
-1
Growth Rate:
-0.63%
Total runs:
148
Run Growth:
-99
Growth Rate:
-66.89%
Total runs:
147
Run Growth:
-37
Growth Rate:
-25.87%
Total runs:
140
Run Growth:
8
Growth Rate:
5.80%
Total runs:
139
Run Growth:
-41
Growth Rate:
-30.15%
Total runs:
138
Run Growth:
53
Growth Rate:
39.55%
Total runs:
137
Run Growth:
12
Growth Rate:
8.82%
Total runs:
124
Run Growth:
20
Growth Rate:
16.95%
Total runs:
124
Run Growth:
30
Growth Rate:
25.64%
Total runs:
123
Run Growth:
38
Growth Rate:
31.40%
Total runs:
120
Run Growth:
10
Growth Rate:
8.62%
Total runs:
115
Run Growth:
10
Growth Rate:
9.43%
Total runs:
114
Run Growth:
16
Growth Rate:
14.81%
Total runs:
114
Run Growth:
21
Growth Rate:
19.44%
Total runs:
112
Run Growth:
19
Growth Rate:
17.76%
Total runs:
111
Run Growth:
8
Growth Rate:
7.48%
Total runs:
111
Run Growth:
10
Growth Rate:
9.35%
Total runs:
109
Run Growth:
7
Growth Rate:
6.73%
Total runs:
108
Run Growth:
30
Growth Rate:
28.04%
Total runs:
108
Run Growth:
15
Growth Rate:
14.29%
Total runs:
108
Run Growth:
0
Growth Rate:
0.00%
Total runs:
107
Run Growth:
14
Growth Rate:
13.73%
Total runs:
106
Run Growth:
14
Growth Rate:
14.00%
Total runs:
106
Run Growth:
5
Growth Rate:
4.90%
Total runs:
106
Run Growth:
16
Growth Rate:
15.38%
Total runs:
106
Run Growth:
15
Growth Rate:
15.15%
Total runs:
106
Run Growth:
14
Growth Rate:
13.59%
Total runs:
106
Run Growth:
6
Growth Rate:
5.88%
Total runs:
106
Run Growth:
19
Growth Rate:
19.00%
Total runs:
105
Run Growth:
-6
Growth Rate:
-6.00%
Total runs:
105
Run Growth:
3
Growth Rate:
3.03%
Total runs:
105
Run Growth:
18
Growth Rate:
17.82%
Total runs:
105
Run Growth:
16
Growth Rate:
15.84%