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

Openchat 3.6 8B 20240522 AWQ by vaclavkosar

 »  All LLMs  »  vaclavkosar  »  Openchat 3.6 8B 20240522 AWQ   URL Share it on

  9   
  Arxiv:2309.11235   4-bit   Autotrain compatible   Awq Base model:meta-llama/meta-lla... Base model:quantized:meta-llam...   C-rlft   Conversational   Endpoints compatible   Llama   Llama3   Openchat   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/vaclavkosar/openchat-3.6-8b-20240522-AWQ 

Openchat 3.6 8B 20240522 AWQ Benchmarks

LLME Score: 0.18213
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Openchat 3.6 8B 20240522 AWQ (vaclavkosar/openchat-3.6-8b-20240522-AWQ)

Openchat 3.6 8B 20240522 AWQ Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Applications:
coding, chat, general tasks
Primary Use Cases:
coding, chat, general tasks
Limitations:
complex reasoning, mathematical and arithmetic tasks, programming challenges, hallucination of non-existent information, may generate harmful or biased responses
Considerations:
Users should verify critical information obtained from the model and apply additional AI safety measures as needed.
Additional Notes 
This model is optimized for deployment using vLLM and can use tensor parallelism for performance improvements.
Input Output 
Input Format:
JSON objects with message list and 'role' and 'content' fields
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Set `<|end_of_turn|>` as end of generation token for best performance.
LLM NameOpenchat 3.6 8B 20240522 AWQ
Repository 🤗https://huggingface.co/vaclavkosar/openchat-3.6-8b-20240522-AWQ 
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM5.8 GB
Updated2025-04-01
Maintainervaclavkosar
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Openchat 3.6 8B 20240522 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB60
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB121
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB274
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB90
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB90
Llama 3 8B Instruct AWQ8K / 5.8 GB1315523
Llama 3 ELYZA JP 8B AWQ8K / 5.8 GB17914
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB6785
...eta Llama 3 8B Instruct Hf AWQ8K / 5.8 GB5598
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB50
Note: green Score (e.g. "73.2") means that the model is better than vaclavkosar/openchat-3.6-8b-20240522-AWQ.

Rank the Openchat 3.6 8B 20240522 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? 45842 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