Japanese Stablelm Instruct Beta 70B GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Japanese Stablelm Instruct Beta 70B GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:quantized:stability... Base model:stabilityai/japanes... Dataset:kunishou/databricks-do... Dataset:kunishou/hh-rlhf-49k-j...   Dataset:kunishou/oasst1-89k-ja   Gptq   Instruct   Ja   Japanese-stablelm   Llama   Quantized   Region:us   Safetensors

Japanese Stablelm Instruct Beta 70B GPTQ Benchmarks

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 Beta 70B GPTQ (TheBloke/japanese-stablelm-instruct-beta-70B-GPTQ)

Japanese Stablelm Instruct Beta 70B GPTQ Parameters and Internals

Model Type 
llama, text-generation
Use Cases 
Areas:
Research, Application-specific fine-tuning
Limitations:
May contain offensive or inappropriate content after applying data cleansing filters
Considerations:
Exercise caution when using these models in production systems.
Supported Languages 
ja (High)
Training Details 
Data Sources:
kunishou/hh-rlhf-49k-ja, kunishou/databricks-dolly-15k-ja, kunishou/oasst1-89k-ja
Methodology:
Fine-tuned on Databricks Dolly-15k, Anthropic HH, and other public data.
Model Architecture:
Llama2 transformer architecture
Input Output 
Input Format:
('~~[INST] <>\nใ‚ใชใŸใฏๅฝน็ซ‹ใคใ‚ขใ‚ทใ‚นใ‚ฟใƒณใƒˆใงใ™ใ€‚<>\n\n{prompt} [/INST]')
Accepted Modalities:
text
Output Format:
text
LLM NameJapanese Stablelm Instruct Beta 70B GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/japanese-stablelm-instruct-beta-70B-GPTQ 
Model NameJapanese StableLM Instruct Beta 70B
Model CreatorStability AI
Base Model(s)  ...ese Stablelm Instruct Beta 70B   stabilityai/japanese-stablelm-instruct-beta-70b
Model Size70b
Required VRAM35.3 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  35.3 GB
Supported Languagesja
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Japanese Stablelm Instruct Beta 70B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB22905
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB522
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB3544
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB82716
...erkrautLM 70B Instruct GPTQ 8B8K / 74.4 GB4151
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB47019
...ama 3 Taiwan 70B Instruct GPTQ8K / 39.8 GB212
...ta Llama 3 70B Instruct Marlin8K / 39.5 GB3766
...g Llama 3 70B Instruct GPTQ 8B8K / 74.4 GB41
...g Llama 3 70B Instruct GPTQ 4B8K / 39.8 GB80
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/japanese-stablelm-instruct-beta-70B-GPTQ.

Rank the Japanese Stablelm Instruct Beta 70B GPTQ Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40123 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217