Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit By Yhyu13: Benchmarks, Features and Detailed Analysis. Insights on Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit.

2bit Autotrain compatible Endpoints compatible Gptq Llama Pytorch Quantized Region:us

Model Card on HF 🤗: https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-2bit

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit Benchmarks

ARC: 61.35 vs 96.7 (so35)^-36.6%

HellaSwag: 83.8 vs 95.3 (gpt4)^-12.1%

MMLU: 57.89 vs 88.3 (so35)^-34.4%

TruthfulQA: 51.18 vs 59 (gpt4)^-13.3%

WinoGrande: 78.77 vs 87.5 (gpt4)^-10%

GSM8K: 31.46 vs 96.4 (so35)^-67.4%

LLME Score: 0.14147

^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)

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit (Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-2bit)

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit Parameters and Internals

Model Type

text generation

Additional Notes

This model version is generated for compatibility with textgen-webui using 2-bit GPTQ quantization, created using scripts from Yhyu13's Gitee repository.

LLM Name	Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit
Repository 🤗	https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-2bit
Base Model(s)	...t Rlhf 2 Llama 30B 7K Steps Hf Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-hf
Model Size	30b
Required VRAM	9.5 GB
Updated	2025-02-21
Maintainer	Yhyu13
Model Type	llama
Model Files	9.5 GB
GPTQ Quantization	Yes
Quantization Type	gptq\|2bit
Model Architecture	LlamaForCausalLM
Context Length	2048
Model Max Length	2048
Transformers Version	4.28.1
Tokenizer Class	LlamaTokenizer
Vocabulary Size	32006
Torch Data Type	float16

Best Alternatives to Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit

Best Alternatives	Context / RAM	Downloads	Likes
GPlatty 30B SuperHOT 8K GPTQ	8K / 16.9 GB	18	7
... 30B Supercot SuperHOT 8K GPTQ	8K / 16.9 GB	21	5
Platypus 30B SuperHOT 8K GPTQ	8K / 16.9 GB	18	4
Tulu 30B SuperHOT 8K GPTQ	8K / 16.9 GB	15	5
Yayi2 30B Llama GPTQ	4K / 17 GB	42	2
WizardLM 30B GPTQ	2K / 16.9 GB	2009	19
Llama 30B FINAL MODEL MINI	2K / 19.4 GB	5	1
...Assistant SFT 7 Llama 30B GPTQ	2K / 16.9 GB	2042	35
WizardLM 30B V1.0 GPTQ	2K / 16.9 GB	3	1
...2 Llama 30B 7K Steps Gptq 4bit	2K / 17.5 GB	7	3

Note: green Score (e.g. "73.2") means that the model is better than Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-2bit.

Rank the Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit 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? 43508 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

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit by Yhyu13

» All LLMs » Yhyu13 » Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit URL Share it on

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit Benchmarks

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit Parameters and Internals

Best Alternatives to Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit

Rank the Oasst Rlhf 2 Llama 30B 7K Steps Gptq 2bit Capabilities

What open-source LLMs or SLMs are you in search of? 43508 in total.