MelloGPT By steve-cse: Benchmarks, Features and Detailed Analysis. Insights on MelloGPT.

Autotrain compatible Conversational Dataset:nbertagnolli/counsel-c... Endpoints compatible Instruct Mistral Model-index Pytorch Region:us Sharded

MelloGPT Benchmarks

ARC: 53.84 vs 96.7 (so35)^-44.3%

HellaSwag: 76.12 vs 95.3 (gpt4)^-20.1%

MMLU: 55.99 vs 88.3 (so35)^-36.6%

TruthfulQA: 55.61 vs 59 (gpt4)^-5.7%

WinoGrande: 73.88 vs 87.5 (gpt4)^-15.6%

GSM8K: 30.1 vs 96.4 (so35)^-68.8%

LLME Score: 0.21981

^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)

MelloGPT Parameters and Internals

LLM Name	MelloGPT
Repository 🤗	https://huggingface.co/steve-cse/MelloGPT
Model Size	7b
Required VRAM	14.4 GB
Updated	2024-09-07
Maintainer	steve-cse
Model Type	mistral
Instruction-Based	Yes
Model Files	4.9 GB: 1-of-3 5.0 GB: 2-of-3 4.5 GB: 3-of-3
Model Architecture	MistralForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.37.0.dev0
Tokenizer Class	LlamaTokenizer
Padding Token	</s>
Vocabulary Size	32000
Torch Data Type	bfloat16

Quantized Models of the MelloGPT

Model	Likes	Downloads	VRAM
MelloGPT GGUF	6	201	3 GB
MelloGPT AWQ	3	9	4 GB
MelloGPT GPTQ	1	11	4 GB

Best Alternatives to MelloGPT

Best Alternatives	Context / RAM	Downloads	Likes
...daz Web AI ChatML 512K Project	512K / 14.5 GB	17	0
... Summarize 64K QLoRANET Merged	128K / 4.1 GB	5	0
...1 Summarize 64K LoRANET Merged	128K / 14.4 GB	7	0
Mistral 7B Instruct V0.2	32K / 14.4 GB	1081846	2499
Mistral 7B Instruct V0.1	32K / 14.4 GB	627662	1495
...ty Instruct 3M 0613 Mistral 7B	32K / 14.4 GB	5284	10
...ty Instruct 3M 0625 Mistral 7B	32K / 14.4 GB	2053	2
Dolphin 2.8 Mistral 7B V02	32K / 14.4 GB	24045	205
XLAM 7B R	32K / 14.4 GB	90	18
...lExperiment 7B MagicCoder V7.5	32K / 14.4 GB	5139	6

Note: green Score (e.g. "73.2") means that the model is better than steve-cse/MelloGPT.

Rank the MelloGPT 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? 35693 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