Opt 6.7B By facebook: Benchmarks, Features and Detailed Analysis. Insights on Opt 6.7B.

Arxiv:2005.14165 Arxiv:2205.01068 Autotrain compatible En Jax Opt Pytorch Region:us Sharded Tf

Opt 6.7B Benchmarks

ARC: 39.16 vs 96.7 (so35)^-59.5%

HellaSwag: 68.66 vs 95.3 (gpt4)^-28%

MMLU: 24.57 vs 88.3 (so35)^-72.2%

TruthfulQA: 35.12 vs 59 (gpt4)^-40.5%

WinoGrande: 65.98 vs 87.5 (gpt4)^-24.6%

GSM8K: 0.99 vs 96.4 (so35)^-99%

LLME Score: 0.13007

^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)

Opt 6.7B Parameters and Internals

LLM Name	Opt 6.7B
Repository 🤗	https://huggingface.co/facebook/opt-6.7b
Model Size	6.7b
Required VRAM	13.4 GB
Updated	2024-09-16
Maintainer	facebook
Model Type	opt
Model Files	10.0 GB: 1-of-2 3.4 GB: 2-of-2
Supported Languages	en
Model Architecture	OPTForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.21.0.dev0
Beginning of Sentence Token	</s>
End of Sentence Token	</s>
Unk Token	</s>
Vocabulary Size	50272
Torch Data Type	float16
Activation Function	relu
Errors	replace

Quantized Models of the Opt 6.7B

Model	Likes	Downloads	VRAM
Opt 6.7B Gptq 4bit	0	89	4 GB

Best Alternatives to Opt 6.7B

Best Alternatives	Context / RAM	Downloads	Likes
....7B Qcqa Ub 16 Best For Q Loss	2K / 27.4 GB	57	0
...B Qcqa Ub 16 Best For KV Cache	2K / 27.4 GB	59	0
...7B Gqa Ub 16 Best For KV Cache	2K / 27.4 GB	60	0
Galactica 6.7B ReFT GSM8k	2K / 13.8 GB	62	0
Galactica 6.7B EssayWriter	2K / 13.4 GB	717	3
Opt Flan Iml 6.7B	2K / 26.6 GB	717	1
...lactica 6.7B Evol Instruct 70K	2K / 27.4 GB	677	19
OPT 6.7B Nerybus Mix	2K / 13.7 GB	1125	20
Galactica 6.7B Finetuned	2K / 27.4 GB	694	34
OPI Galactica 6.7B	2K / 0 GB	31	4

Note: green Score (e.g. "73.2") means that the model is better than facebook/opt-6.7b.

Rank the Opt 6.7B 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? 35926 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 v2024072803

Support LLM Explorer