Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 By llm-jp: Benchmarks, Features and Detailed Analysis. Insights on Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1.

Arxiv:2305.18290 Dataset:llm-jp/hh-rlhf-12k-ja En Ja Lora Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/llm-jp/llm-jp-13b-dpo-lora-hh_rlhf_ja-v1.1

Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 Benchmarks

^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)

Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 (llm-jp/llm-jp-13b-dpo-lora-hh_rlhf_ja-v1.1)

🌟 Advertise your project 🚀

Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 Parameters and Internals

Model Type

Transformer-based Language Model, text-generation

Use Cases

Areas:

research, commercial applications

Applications:

Natural Language Processing

Primary Use Cases:

text generation

Limitations:

Not tuned for outputs that align with human intent and safety considerations.

Additional Notes

Models released are in the early stages of research and development.

Supported Languages

en (English), ja (Japanese)

Training Details

Data Sources:

Wikipedia, mC4, The Pile, The Stack

Data Volume:

300B tokens

Methodology:

Direct Preference Optimization

Context Length:

2048

Hardware Used:

96 A100 40GB GPUs for pre-training, 8 A100 40GB GPUs for instruction tuning

Model Architecture:

Hugging Face Transformers

Input Output

Accepted Modalities:

text

Output Format:

text

LLM Name	Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1
Repository 🤗	https://huggingface.co/llm-jp/llm-jp-13b-dpo-lora-hh_rlhf_ja-v1.1
Model Size	13b
Required VRAM	0.8 GB
Updated	2025-08-16
Maintainer	llm-jp
Model Files	0.8 GB
Supported Languages	en ja
Model Architecture	AutoModel
License	apache-2.0
Is Biased	none
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad\|LLM-jp>
PEFT Type	LORA
LoRA Model	Yes
PEFT Target Modules	c_proj\|c_attn\|c_fc
LoRA Alpha	256
LoRA Dropout	0.05
R Param	128

Best Alternatives to Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1

Best Alternatives	Context / RAM	Downloads	Likes
Nous Hermes Llama2 Llamafile	0K / GB	259	2
BimoGPT Llama2 13B	0K / 0.6 GB	0	7
Llama2 13B Chinese Chat	0K / 0 GB	0	39
PhysicsLlama 13B	0K / 0 GB	0	1
...fast Codellama 13B Instruct Hf	0K / 13 GB	1	1
...lama 2 13B Alpaca Spanish LoRA	0K / 1.7 GB	0	2
Medalpaca Lora 13B 8bit	0K / 0.1 GB	0	1
MythoMax L2 13B GGUF	0K / 5.4 GB	124181	173
Llama 3 13B Instruct V0.1 GGUF	0K / 5.1 GB	1224	5
Hermes 2 Pro Llama 3 13B GGUF	0K / 4.6 GB	51	0

Note: green Score (e.g. "73.2") means that the model is better than llm-jp/llm-jp-13b-dpo-lora-hh_rlhf_ja-v1.1.

Rank the Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 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? 50723 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 v20241124

Support LLM Explorer

Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 by llm-jp

» All LLMs » llm-jp » Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 URL Share it on

Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 Benchmarks

Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 Parameters and Internals

Best Alternatives to Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1

Rank the Llm Jp 13B DPO Lora Hh Rlhf Ja V1.1 Capabilities

What open-source LLMs or SLMs are you in search of? 50723 in total.