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

Yarn Llama 2 7B 64K AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Yarn Llama 2 7B 64K AWQ   URL Share it on

  18   
  Arxiv:2309.00071   4-bit   Autotrain compatible   Awq Base model:nousresearch/yarn-l... Base model:quantized:nousresea...   Custom code   Dataset:pg19   Llama   Quantized   Region:us   Safetensors   Yarn
Model Card on HF 🤗: https://huggingface.co/TheBloke/Yarn-Llama-2-7B-64K-AWQ 

Yarn Llama 2 7B 64K AWQ Benchmarks

LLME Score: 0.13863
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yarn Llama 2 7B 64K AWQ (TheBloke/Yarn-Llama-2-7B-64K-AWQ)

Yarn Llama 2 7B 64K AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Considerations:
The model is intended for long-context applications.
Additional Notes 
AWQ is a low-bit weight quantization method that supports 4-bit quantization, offering faster inference but potentially lower throughput compared to unquantized models.
Training Details 
Data Sources:
PG19 dataset
Methodology:
Started from the base Llama 2 models, further pretrained on a subset of the PG19 dataset for 400 steps.
Context Length:
64000
Input Output 
Input Format:
{prompt}
Output Format:
Expected to generate text outputs based on the given prompt.
LLM NameYarn Llama 2 7B 64K AWQ
Repository 🤗https://huggingface.co/TheBloke/Yarn-Llama-2-7B-64K-AWQ 
Model NameYarn Llama 2 7B 64K
Model CreatorNousResearch
Base Model(s)  Yarn Llama 2 7B 64K   NousResearch/Yarn-Llama-2-7b-64k
Model Size7b
Required VRAM3.9 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Model Files  3.9 GB
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length65536
Model Max Length65536
Transformers Version4.32.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Yarn Llama 2 7B 64K AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 AWQ195K / 19.3 GB101
Calm2 7B Chat AWQ32K / 4.4 GB612
Llama 2 7B 32K Instruct AWQ32K / 3.9 GB222
... SWE Llama 7B Updated 4bit AWQ16K / 3.9 GB160
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB23590
Pandalyst 7B V1.2 AWQ16K / 3.9 GB231
Tora Code 7B V1.0 AWQ16K / 3.9 GB200
...eechless Tora Code 7B V1.0 AWQ16K / 3.9 GB221
CodeLlama 7B Instruct AWQ16K / 3.9 GB1764
Pandalyst 7B V1.1 AWQ16K / 3.9 GB321
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Yarn-Llama-2-7B-64K-AWQ.

Rank the Yarn Llama 2 7B 64K 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? 40066 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 v20241217
  Support LLM Explorer