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

AwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2 by Zoyd

 »  All LLMs  »  Zoyd  »  AwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2   URL Share it on

  6   
  Autotrain compatible   Conversational   Endpoints compatible   Exl2   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Zoyd/AwanLLM_Awanllm-Llama-3-8B-Cumulus-v1.0-6_5bpw_exl2 

AwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2 Benchmarks

LLME Score: 0.19051
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
AwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2 (Zoyd/AwanLLM_Awanllm-Llama-3-8B-Cumulus-v1.0-6_5bpw_exl2)

AwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
general use cases, story writing, RP use cases
Limitations:
probably a bit worse than the OG Meta Llama 3 8B Instruct in terms of reasoning and intelligence
Considerations:
Be precise and explain what you want the model to do. Use system prompts that tell it that it is the character.
Additional Notes 
EXL2 quantized model with variations in size and head listed. Most uncensored model, based on uncensored base model.
Training Details 
Methodology:
Using 4-bit loading and Qlora 64-rank 64-alpha resulting in ~2% trainable weights
Context Length:
8192
Training Time:
around 4 days on an RTX 4090
Hardware Used:
RTX 4090
Input Output 
Input Format:
<|begin_of_text|><|start_header_id|>system<|end_header_id|> {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|> {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|> {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
Performance Tips:
Be precise and explain what you want the model to do. It has less base 'personality' than the OG model but will act as instructed.
Release Notes 
Version:
v1.0
Notes:
Aims to be uncensored with zero refusals and zero warnings. Especially better for story writing or RP use cases.
LLM NameAwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2
Repository 🤗https://huggingface.co/Zoyd/AwanLLM_Awanllm-Llama-3-8B-Cumulus-v1.0-6_5bpw_exl2 
Model Size8b
Required VRAM7.2 GB
Updated2025-02-22
MaintainerZoyd
Model Typellama
Instruction-BasedYes
Model Files  7.2 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to AwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB212
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB71
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB102
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB70
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1225
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB2817
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB83
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB71
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB111
Note: green Score (e.g. "73.2") means that the model is better than Zoyd/AwanLLM_Awanllm-Llama-3-8B-Cumulus-v1.0-6_5bpw_exl2.

Rank the AwanLLM Awanllm Llama 3 8B Cumulus V1.0 6 5bpw EXL2 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