SUS Chat 34B By SUSTech: Benchmarks, Features and Detailed Analysis. Insights on SUS Chat 34B.

Autotrain compatible Doi:10.57967/hf/1718 Endpoints compatible Llama Pytorch Region:us Sharded

SUS Chat 34B Benchmarks

ARC: 97.7^1.5%

HellaSwag: 94.2^-1.2%

MMLU: 75.9^-12.3%

TruthfulQA: 57.04^-3.3%

WinoGrande: 83.5^-4.6%

GSM8K: 72.3^-21.4%

OpenCompass Avg: 64.3 vs 73.3 (GPT-4) ^-12.3%

Exam: 81.5^5.6%

Language: 38.2^-38.4%

Knowledge: 62.7^-14.7%

Understanding: 74.1^5.9%

Reasoning: 63.9^-14.1%

^nn.n% — How the model compares to the GPT-4.

SUS Chat 34B Parameters and Internals

LLM Name	SUS Chat 34B
Repository	Open on 🤗
Model Size	34b
Required VRAM	68.9 GB
Updated	2024-07-27
Maintainer	SUSTech
Model Type	llama
Model Files	10.0 GB: 1-of-7 9.9 GB: 2-of-7 9.8 GB: 3-of-7 9.8 GB: 4-of-7 9.8 GB: 5-of-7 9.9 GB: 6-of-7 9.7 GB: 7-of-7
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	8192
Model Max Length	8192
Transformers Version	4.35.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	64000
Torch Data Type	bfloat16

Quantized Models of the SUS Chat 34B

Model	Likes	Downloads	VRAM
SUS Chat 34B GGUF	16	258	14 GB
SUS Chat 34B AWQ	9	18	19 GB
SUS Chat 34B GPTQ	3	12	18 GB

Best Alternatives to SUS Chat 34B

Best Alternatives	HF Rank	Context/RAM	Downloads	Likes
Yi 34B 200K	0.3	195K / 68.9 GB	5247	313
Smaug 34B V0.1	0.3	195K / 69.2 GB	3185	58
Yi 34B 200K AEZAKMI V2	0.3	195K / 69.2 GB	948	12
Smaug 34B V0.1 ExPO	0.3	195K / 69.2 GB	2085	0
Faro Yi 34B	0.3	195K / 69.2 GB	2748	6
Bagel DPO 34B V0.5	0.3	195K / 68.7 GB	1861	17
Nous Capybara 34B	0.3	195K / 68.9 GB	6259	242
Yi 34B 200K HESOYAM 0905	0.3	195K / 69.2 GB	240	0
Bagel DPO 34B V0.2	0.3	195K / 69.2 GB	2769	97
34B Beta	0.3	195K / 69.2 GB	1221	59

Note: green Score (e.g. "73.2") means that the model is better than SUSTech/SUS-Chat-34B.

Rank the SUS Chat 34B 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? 34447 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 v2024072501

Support LLM Explorer