Tess V2.5 Qwen2 72B By migtissera: Benchmarks, Features and Detailed Analysis. Insights on Tess V2.5 Qwen2 72B.

Merged Model Autotrain compatible Conversational Endpoints compatible Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/migtissera/Tess-v2.5-Qwen2-72B

Tess V2.5 Qwen2 72B Benchmarks

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Tess V2.5 Qwen2 72B (migtissera/Tess-v2.5-Qwen2-72B)

Tess V2.5 Qwen2 72B Parameters and Internals

Model Type

Large Language Model

Use Cases

Areas:

research, commercial applications

Limitations:

Can produce inaccurate or misleading results., Possibility of generating inappropriate, biased, or offensive content.

Additional Notes

The model uses Tesoro as its assistant identity. It is a state-of-the-art model with significant improvements in reasoning, coding, and mathematics capabilities.

Training Details

Data Sources:

Tess-v2.5 dataset

Data Volume:

300K samples

Methodology:

Fine-tuning with low learning rates, low number of epochs, high quality and diverse data.

Training Time:

4 days

Hardware Used:

4xA100 VM on Microsoft Azure

Input Output

Input Format:

ChatML prompt format

Accepted Modalities:

text

Performance Tips:

Add 'No follow-up questions necessary' to system prompt to prevent follow-up questions.

Release Notes

Version:

v2.5

Notes:

Added feature for follow-up questions. Fixed stop token issues.

Version:

v2.5.2

Notes:

Fixed issue with stop token generation.

LLM Name	Tess V2.5 Qwen2 72B
Repository 🤗	https://huggingface.co/migtissera/Tess-v2.5-Qwen2-72B
Merged Model	Yes
Model Size	72b
Required VRAM	146 GB
Updated	2025-02-22
Maintainer	migtissera
Model Type	qwen2
Model Files	4.5 GB: 1-of-31 5.0 GB: 2-of-31 4.8 GB: 3-of-31 4.8 GB: 4-of-31 4.8 GB: 5-of-31 5.0 GB: 6-of-31 4.8 GB: 7-of-31 4.8 GB: 8-of-31 4.8 GB: 9-of-31 5.0 GB: 10-of-31 4.8 GB: 11-of-31 4.8 GB: 12-of-31 4.8 GB: 13-of-31 5.0 GB: 14-of-31 4.8 GB: 15-of-31 4.8 GB: 16-of-31 4.8 GB: 17-of-31 5.0 GB: 18-of-31 4.8 GB: 19-of-31 4.8 GB: 20-of-31 4.8 GB: 21-of-31 5.0 GB: 22-of-31 4.8 GB: 23-of-31 4.8 GB: 24-of-31 4.8 GB: 25-of-31 5.0 GB: 26-of-31 4.8 GB: 27-of-31 4.8 GB: 28-of-31 4.8 GB: 29-of-31 3.2 GB: 30-of-31 2.5 GB: 31-of-31
Model Architecture	Qwen2ForCausalLM
License	other
Context Length	131072
Model Max Length	131072
Transformers Version	4.41.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|end_of_text\|>
Vocabulary Size	152064
Torch Data Type	float16
Errors	replace

Quantized Models of the Tess V2.5 Qwen2 72B

Model	Likes	Downloads	VRAM
Tess V2.5.2 Qwen2 72B AWQ	0	14	41 GB

Best Alternatives to Tess V2.5 Qwen2 72B

Best Alternatives	Context / RAM	Downloads	Likes
Ultiima 72B	128K / 146.1 GB	2144	1
EVA Qwen2.5 72B V0.2	128K / 146 GB	2394	16
Qwen2.5 72B	128K / 145.5 GB	26010	58
Ultiima 72B V1.5	128K / 146.1 GB	112	0
AceInstruct 72B	128K / 146 GB	187	14
Homer V1.0 Qwen2.5 72B	128K / 146.1 GB	126	6
Qwen2 72B	128K / 145.5 GB	9582	197
Dolphin 2.9.2 Qwen2 72B	128K / 146 GB	7661	155
...n2.5 72B 2x Instruct TIES V1.0	128K / 146.1 GB	8	0
Calme 2.3 Qwen2 72B	128K / 146 GB	1916	2

Note: green Score (e.g. "73.2") means that the model is better than migtissera/Tess-v2.5-Qwen2-72B.

Rank the Tess V2.5 Qwen2 72B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 43470 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Release v20241227

Support LLM Explorer