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

Llama2 70B SpellBlade by sequelbox

 »  All LLMs  »  sequelbox  »  Llama2 70B SpellBlade   URL Share it on

  5   
  Autotrain compatible   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/sequelbox/Llama2-70B-SpellBlade 

Llama2 70B SpellBlade Benchmarks

LLME Score: 0.15261
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama2 70B SpellBlade (sequelbox/Llama2-70B-SpellBlade)

Llama2 70B SpellBlade Parameters and Internals

Use Cases 
Limitations:
Legacy model offered primarily for reference purposes.
Considerations:
Recommend using Llama 3 over this model for general use.
Additional Notes 
Performs solidly as-is, but further finetuning is recommended to optimize user satisfaction.
Training Details 
Methodology:
Finetuned to improve conversational quality and supplement technical capability. Utilizes [INST][/INST] chat format.
Input Output 
Input Format:
[INST][/INST] chat format
Performance Tips:
User satisfaction will be optimized with further finetuning.
LLM NameLlama2 70B SpellBlade
Repository 🤗https://huggingface.co/sequelbox/Llama2-70B-SpellBlade 
Model Size70b
Required VRAM212 GB
Updated2025-02-22
Maintainersequelbox
Model Typellama
Model Files  4.8 GB: 1-of-61   4.6 GB: 2-of-61   4.4 GB: 3-of-61   5.0 GB: 4-of-61   4.4 GB: 5-of-61   4.4 GB: 6-of-61   5.0 GB: 7-of-61   4.4 GB: 8-of-61   4.4 GB: 9-of-61   5.0 GB: 10-of-61   4.4 GB: 11-of-61   4.4 GB: 12-of-61   5.0 GB: 13-of-61   4.4 GB: 14-of-61   4.4 GB: 15-of-61   5.0 GB: 16-of-61   4.4 GB: 17-of-61   4.4 GB: 18-of-61   5.0 GB: 19-of-61   4.4 GB: 20-of-61   4.4 GB: 21-of-61   5.0 GB: 22-of-61   4.4 GB: 23-of-61   4.4 GB: 24-of-61   5.0 GB: 25-of-61   4.4 GB: 26-of-61   4.4 GB: 27-of-61   5.0 GB: 28-of-61   4.4 GB: 29-of-61   4.4 GB: 30-of-61   5.0 GB: 31-of-61   4.4 GB: 32-of-61   4.4 GB: 33-of-61   5.0 GB: 34-of-61   4.4 GB: 35-of-61   4.4 GB: 36-of-61   5.0 GB: 37-of-61   4.4 GB: 38-of-61   4.4 GB: 39-of-61   5.0 GB: 40-of-61   4.4 GB: 41-of-61   4.4 GB: 42-of-61   5.0 GB: 43-of-61   4.4 GB: 44-of-61   4.4 GB: 45-of-61   5.0 GB: 46-of-61
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Llama2 70B SpellBlade

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB40355
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB25245
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB199121
Llama3 Function Calling 1048K1024K / 141.9 GB61
...a 3 70B Instruct Gradient 524K512K / 141.9 GB23323
...a 3 70B Instruct Gradient 262K256K / 141.9 GB18655
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB3212
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB653
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB120
Yi 70B 200K RPMerge Franken195K / 142.4 GB101
Note: green Score (e.g. "73.2") means that the model is better than sequelbox/Llama2-70B-SpellBlade.

Rank the Llama2 70B SpellBlade 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