LLM EXPLORER 62,076 MODELS INDEXED

Swallow 70B Instruct GPTQ by TheBloke

By TheBloke · 7 downloads
HF Repo ↗ Copy URL

Swallow 70B Instruct GPTQ is an open-source language model by TheBloke. Features: 70b LLM, VRAM: 35.7GB, Context: 4K, License: llama2, Quantized, Instruction-Based, LLM Explorer Score: 0.1.

  4-bit Base model:quantized:tokyotech... Base model:tokyotech-llm/swall...   En   Gptq   Instruct   Ja   Llama   Quantized   Region:us   Safetensors
Model Card on HF ๐Ÿค—: https://huggingface.co/TheBloke/Swallow-70B-instruct-GPTQ 

Swallow 70B Instruct GPTQ Parameters and Internals

Model Type 
llama
Use Cases 
Limitations:
Not tuned to ensure outputs align with human intent and safety considerations.
Supported Languages 
en (English), ja (Japanese)
Training Details 
Data Sources:
Japanese Wikipedia, RefinedWeb, Swallow Corpus, The Pile
Methodology:
Continual Pre-Training
Model Architecture:
LLaMA-2
Input Output 
Input Format:
ไปฅไธ‹ใซใ€ใ‚ใ‚‹ใ‚ฟใ‚นใ‚ฏใ‚’่ชฌๆ˜Žใ™ใ‚‹ๆŒ‡็คบใŒใ‚ใ‚Šใพใ™ใ€‚ใƒชใ‚ฏใ‚จใ‚นใƒˆใ‚’้ฉๅˆ‡ใซๅฎŒไบ†ใ™ใ‚‹ใŸใ‚ใฎๅ›ž็ญ”ใ‚’่จ˜่ฟฐใ—ใฆใใ ใ•ใ„ใ€‚ ### ๆŒ‡็คบ: {prompt} ### ๅฟœ็ญ”:
LLM NameSwallow 70B Instruct GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Swallow-70B-instruct-GPTQ 
Model NameSwallow 70B Instruct
Model Creatortokyotech-llm
Base Model(s)  Swallow 70B Instruct Hf   tokyotech-llm/Swallow-70b-instruct-hf
Model Size70b
Required VRAM35.7 GB
Updated2026-04-26
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  35.7 GB
Supported Languagesen ja
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size43176
Torch Data Typebfloat16

Best Alternatives to Swallow 70B Instruct GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB5176
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB1290
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB74
...ta Llama 3 70B Instruct Marlin8K / 39.5 GB1416
...ama 3 Taiwan 70B Instruct GPTQ8K / 39.8 GB62
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB90516
Meta Llama 3 70B Instruct GPTQ8K / 39.8 GB76319
...g Llama 3 70B Instruct GPTQ 4B8K / 39.8 GB60
...g Llama 3 70B Instruct GPTQ 8B8K / 74.4 GB31
...a Llama 3 70B Instruct GPTQ 8B8K / 74.4 GB170
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Swallow-70B-instruct-GPTQ.