LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Japanese Stablelm Instruct Gamma 7B DPO Uf V1 by ohwi

 »  All LLMs  »  ohwi  »  Japanese Stablelm Instruct Gamma 7B DPO Uf V1   URL Share it on

  12   
  Arxiv:2310.06825   Autotrain compatible Base model:finetune:ohwi/japan... Base model:ohwi/japanese-stabl...   Conversational Dataset:argilla/ultrafeedback-...   Dataset:llm-jp/hh-rlhf-12k-ja   Endpoints compatible   Instruct   Ja   Japanese-stablelm   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ohwi/japanese-stablelm-instruct-gamma-7b-dpo-uf-v1 

Japanese Stablelm Instruct Gamma 7B DPO Uf V1 Benchmarks

LLME Score: 0.17019
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Japanese Stablelm Instruct Gamma 7B DPO Uf V1 (ohwi/japanese-stablelm-instruct-gamma-7b-dpo-uf-v1)

Japanese Stablelm Instruct Gamma 7B DPO Uf V1 Parameters and Internals

Model Type 
causal-lm, text-generation
Use Cases 
Areas:
General purpose language model, application-specific fine-tuning
Limitations:
The model might generate biased or inappropriate text due to the pre-training dataset., Exercise caution in production.
Supported Languages 
Japanese (Native)
Training Details 
Data Sources:
argilla/ultrafeedback-binarized-preferences-cleaned, llm-jp/hh-rlhf-12k-ja
Methodology:
Fine-tuned on preference datasets
Model Architecture:
Transformer decoder architecture
Input Output 
Input Format:
Input: Prompt with context
Accepted Modalities:
text
Output Format:
Generated text following the prompt
LLM NameJapanese Stablelm Instruct Gamma 7B DPO Uf V1
Repository 🤗https://huggingface.co/ohwi/japanese-stablelm-instruct-gamma-7b-dpo-uf-v1 
Base Model(s)  ohwi/japanese-stablelm-instruct-gamma-7b-repro   ohwi/japanese-stablelm-instruct-gamma-7b-repro
Model Size7b
Required VRAM14.4 GB
Updated2025-02-22
Maintainerohwi
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesja
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Japanese Stablelm Instruct Gamma 7B DPO Uf V1

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB462011
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB120
...1 Summarize 64K LoRANET Merged128K / 14.4 GB110
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB1916301573
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37505
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB37063
Note: green Score (e.g. "73.2") means that the model is better than ohwi/japanese-stablelm-instruct-gamma-7b-dpo-uf-v1.

Rank the Japanese Stablelm Instruct Gamma 7B DPO Uf V1 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