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

Dolphin 2.2 70B 5.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Dolphin 2.2 70B 5.0bpw H6 EXL2   URL Share it on

  11   
  Merged Model   Autotrain compatible   Dataset:ehartford/dolphin Dataset:ehartford/samantha-dat... Dataset:ehartford/wizardlm evo... Dataset:jondurbin/airoboros-2....   En   Endpoints compatible   Exl2   Instruct   Llama   Pytorch   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/dolphin-2.2-70b-5.0bpw-h6-exl2 

Dolphin 2.2 70B 5.0bpw H6 EXL2 Benchmarks

LLME Score: 0.15108
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin 2.2 70B 5.0bpw H6 EXL2 (LoneStriker/dolphin-2.2-70b-5.0bpw-h6-exl2)

Dolphin 2.2 70B 5.0bpw H6 EXL2 Parameters and Internals

Model Type 
conversation, empathy, uncensored
Use Cases 
Areas:
commercial, non-commercial
Primary Use Cases:
conversation advising, empathetic responses
Considerations:
Implement your own alignment layer before exposing the model as a service.
Additional Notes 
You are responsible for any content you create using this model. Enjoy responsibly.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/samantha-data, ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
Methodology:
qLoRA and Axolotl
Training Time:
5 days
Hardware Used:
4x A100s
Input Output 
Input Format:
ChatML
Accepted Modalities:
text
LLM NameDolphin 2.2 70B 5.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/dolphin-2.2-70b-5.0bpw-h6-exl2 
Merged ModelYes
Model Size70b
Required VRAM43.6 GB
Updated2024-12-21
MaintainerLoneStriker
Model Typellama
Instruction-BasedYes
Model Files  8.6 GB: 1-of-6   8.5 GB: 2-of-6   8.5 GB: 3-of-6   8.5 GB: 4-of-6   8.6 GB: 5-of-6   0.9 GB: 6-of-6
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Dolphin 2.2 70B 5.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 8bit1024K / 75 GB145
...B Instruct Gradient 1048K 4bit1024K / 39.7 GB163
...B Instruct Gradient 1048K 2bit1024K / 21.9 GB112
...0B Instruct Gradient 262K 4bit256K / 39.7 GB153
...0B Instruct Gradient 262K 8bit256K / 75 GB72
...0B Instruct Gradient 262K 2bit256K / 21.9 GB141
...t Gradient 262K 4.0bpw H6 EXL2256K / 37.2 GB141
... Gradient 262K 2.25bpw H6 EXL2256K / 22.2 GB70
...t Gradient 262K 2.4bpw H6 EXL2256K / 23.5 GB110
...t Gradient 262K 3.5bpw H6 EXL2256K / 32.9 GB50
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/dolphin-2.2-70b-5.0bpw-h6-exl2.

Rank the Dolphin 2.2 70B 5.0bpw H6 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? 40013 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