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

Dolphin 2.7 Mixtral 8x7b AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  Dolphin 2.7 Mixtral 8x7b AWQ   URL Share it on

  6364   
  4-bit   Autotrain compatible   Awq Base model:cognitivecomputatio... Base model:quantized:cognitive...   Conversational   Dataset:ehartford/dolphin Dataset:ehartford/dolphin-code... Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss... Dataset:jondurbin/airoboros-2....   Dataset:ldjnr/capybara   Dataset:teknium/openhermes   En   Instruct   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheBloke/dolphin-2.7-mixtral-8x7b-AWQ 

Dolphin 2.7 Mixtral 8x7b AWQ Benchmarks

LLME Score: 0.19961
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin 2.7 Mixtral 8x7b AWQ (TheBloke/dolphin-2.7-mixtral-8x7b-AWQ)

Dolphin 2.7 Mixtral 8x7b AWQ Parameters and Internals

Model Type 
mixtral
Additional Notes 
This model, being uncensored and highly compliant, requires user-advised alignment handling before deployment as a service. It has undergone retraining with specific fixes aiming to improve performance.
Training Details 
Data Sources:
ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/dolphin-coder, teknium/openhermes, ise-uiuc/Magicoder-OSS-Instruct-75K, ise-uiuc/Magicoder-Evol-Instruct-110K, LDJnr/Capybara
Context Length:
32768
Hardware Used:
4x A100s
Model Architecture:
Mixtral-8x7b
LLM NameDolphin 2.7 Mixtral 8x7b AWQ
Repository 🤗https://huggingface.co/TheBloke/dolphin-2.7-mixtral-8x7b-AWQ 
Model NameDolphin 2.7 Mixtral 8X7B
Model CreatorCognitive Computations
Base Model(s)  cognitivecomputations/dolphin-2.7-mixtral-8x7b   cognitivecomputations/dolphin-2.7-mixtral-8x7b
Model Size6.5b
Required VRAM24.7 GB
Updated2025-02-05
MaintainerTheBloke
Model Typemixtral
Instruction-BasedYes
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   4.7 GB: 3-of-3
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Dolphin 2.7 Mixtral 8x7b AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral Instruct AWQ32K / 24.7 GB437643
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB50
...utLM Mixtral 8x7B Instruct AWQ32K / 24.7 GB14162
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB36457
...xtral Instruct AWQ Clone Dec2332K / 24.7 GB80
...ixtral Instruct 8x7b Zloss AWQ32K / 24.7 GB102
...0.1 LimaRP ZLoss DARE TIES AWQ32K / 24.7 GB43
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB20715
...Instruct V0.1 LimaRP ZLoss AWQ32K / 24.7 GB71
Dolphin 2.6 Mixtral 8x7b AWQ32K / 24.7 GB2013

Rank the Dolphin 2.7 Mixtral 8x7b 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? 42577 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