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

Speechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Speechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ   URL Share it on

  88   
  Arxiv:2307.09288   4-bit   Autotrain compatible   Awq Base model:quantized:uukuguy/s... Base model:uukuguy/speechless-... Dataset:garage-baind/open-plat...   En   Facebook   Llama   Llama2   Meta   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Speechless-Llama2-Hermes-Orca-Platypus-WizardLM-13B-AWQ 

Speechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ Benchmarks

LLME Score: 0.13049
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Speechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ (TheBloke/Speechless-Llama2-Hermes-Orca-Platypus-WizardLM-13B-AWQ)

Speechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
Commercial and research use; optimized for chat use cases.
Applications:
Assistant-like dialogue applications
Primary Use Cases:
Chatbots, customer service automation
Limitations:
Model may produce inaccurate or biased outputs. Safe deployment requires additional testing.
Considerations:
Safety testing should be conducted before application deployment.
Additional Notes 
Model is part of Meta's Llama 2 family and utilizes AWQ for efficient GPU inference.
Training Details 
Data Sources:
NousResearch/Nous-Hermes-Llama2-13b, Open-Orca/OpenOrca-Platypus2-13B, WizardLM/WizardLM-13B-V1.2
Methodology:
The model was pre-trained and fine-tuned using a combination of different language model datasets.
Context Length:
4096
Hardware Used:
A100-80GB GPUs
Model Architecture:
Auto-regressive transformer architecture with optimizations for generative text modeling.
Responsible Ai Considerations 
Fairness:
Model was evaluated for fairness as part of Meta's internal evaluations.
Transparency:
Results from internal evaluations are shared, but use of the model/data may require acceptance of specific agreements.
Mitigation Strategies:
Supervised fine-tuning and Reinforcement Learning from Human Feedback (RLHF) to align outputs to be more helpful.
Input Output 
Input Format:
Text-based input only, formatted using specific prompt templates.
Accepted Modalities:
text
Output Format:
Generated text
LLM NameSpeechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ
Repository 🤗https://huggingface.co/TheBloke/Speechless-Llama2-Hermes-Orca-Platypus-WizardLM-13B-AWQ 
Model NameSpeechess Lllama2 Hermes Orca-Platypus WizardLM 13B
Model CreatorJiangwen Su
Base Model(s)  ...mes Orca Platypus Wizardlm 13B   uukuguy/speechless-llama2-hermes-orca-platypus-wizardlm-13b
Model Size13b
Required VRAM7.2 GB
Updated2025-03-13
MaintainerTheBloke
Model Typellama
Model Files  7.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.32.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Speechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K AWQ128K / 7.2 GB1232
LongAlign 13B 64K AWQ64K / 7.2 GB242
...oboros L2 13B 2 1 YaRN 64K AWQ64K / 7.2 GB1282
OrcaMaid V3 13B 32K AWQ32K / 7.2 GB304
OrcaMaid V2 FIX 13B 32K AWQ32K / 7.2 GB1001
NexusRaven V2 13B AWQ16K / 7.2 GB293
NexusRaven V2 13B AWQ16K / 7.2 GB113
...th CodeLlama 13B Python Hf AWQ16K / 7.5 GB150
WhiteRabbitNeo 13B AWQ16K / 7.2 GB3054
NexusRaven V2 13B AWQ16K / 7.2 GB881
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Speechless-Llama2-Hermes-Orca-Platypus-WizardLM-13B-AWQ.

Rank the Speechless Llama2 Hermes Orca Platypus WizardLM 13B AWQ 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? 44949 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