Llama 3 8B Sft Mixture By OpenRLHF: Benchmarks, Features and Detailed Analysis. Insights on Llama 3 8B Sft Mixture.

Arxiv:2405.07863 Autotrain compatible Conversational Endpoints compatible Llama Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/OpenRLHF/Llama-3-8b-sft-mixture

Llama 3 8B Sft Mixture Benchmarks

LLME Score: 0.24673

^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)

Llama 3 8B Sft Mixture (OpenRLHF/Llama-3-8b-sft-mixture)

Llama 3 8B Sft Mixture Parameters and Internals

Model Type

SFT, text generation

Use Cases

Considerations:

The model is a good starting point for RLHF research.

Training Details

Data Sources:

ShareGPT, Evol-Instruct, SlimOrca, MathInstruct, Magicoder-Evol-Instruct, GPT4-LLM, OrcaMath, GPTeacher, UltraInteract

Methodology:

Trained for 1 epoch on a mixture of diverse open-source high-quality datasets with detailed parameters specified in the report.

Model Architecture:

Derived from Meta-Llama-3-8B

Release Notes

Version:

Latest

Notes:

Fixed generation_config.json. Intended for use in Online-RLHF project, without RLHF training.

LLM Name	Llama 3 8B Sft Mixture
Repository 🤗	https://huggingface.co/OpenRLHF/Llama-3-8b-sft-mixture
Model Size	8b
Required VRAM	16.1 GB
Updated	2025-02-22
Maintainer	OpenRLHF
Model Type	llama
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 4.9 GB: 3-of-4 1.2 GB: 4-of-4
Model Architecture	LlamaForCausalLM
Context Length	8192
Model Max Length	8192
Transformers Version	4.40.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|end_of_text\|>
Vocabulary Size	128256
Torch Data Type	bfloat16

Best Alternatives to Llama 3 8B Sft Mixture

Best Alternatives	Context / RAM	Downloads	Likes
...a 3 8B Instruct Gradient 1048K	1024K / 16.1 GB	3927	680
MrRoboto ProLong 8B V4i	1024K / 16.1 GB	66	1
...o ProLongBASE Pt8 Unaligned 8B	1024K / 16.1 GB	24	0
MrRoboto BASE V2 Unholy 8B 64K	1024K / 16.1 GB	27	1
Mpasila Viking 8B	1024K / 16.1 GB	84	0
Thor V1.4 8B DARK FICTION	1024K / 16.1 GB	941	2
4	1024K / 16.1 GB	322	0
Hel V2 8B DARK FICTION	1024K / 16.1 GB	22	0
16	1024K / 16.1 GB	169	0
...di95 LewdStorytellerMix 8B 64K	1024K / 16.1 GB	69	2

Note: green Score (e.g. "73.2") means that the model is better than OpenRLHF/Llama-3-8b-sft-mixture.

Rank the Llama 3 8B Sft Mixture 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

Llama 3 8B Sft Mixture by OpenRLHF

» All LLMs » OpenRLHF » Llama 3 8B Sft Mixture URL Share it on

Llama 3 8B Sft Mixture Benchmarks

Llama 3 8B Sft Mixture Parameters and Internals

Best Alternatives to Llama 3 8B Sft Mixture

Rank the Llama 3 8B Sft Mixture Capabilities

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