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

Dolphin 2.9.1 Qwen 110B by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Dolphin 2.9.1 Qwen 110B   URL Share it on

  46   
  Autotrain compatible   Axolotl Base model:finetune:qwen/qwen1...   Base model:qwen/qwen1.5-110b   Conversational Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/...   Dataset:internlm/agent-flan Dataset:locutusque/function-ca... Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo...   Dataset:teknium/openhermes-2.5   Endpoints compatible   Generated from trainer   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.9.1-qwen-110b 

Dolphin 2.9.1 Qwen 110B Benchmarks

LLME Score: 0.20409
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin 2.9.1 Qwen 110B (cognitivecomputations/dolphin-2.9.1-qwen-110b)

Dolphin 2.9.1 Qwen 110B Parameters and Internals

Model Type 
instruction, conversational, coding
Use Cases 
Areas:
Instruction, Conversational, Coding
Primary Use Cases:
Instruction, Conversational, Coding
Considerations:
The model is highly compliant and will respond to any request, ethical or unethical. Implement alignment layer before exposure.
Additional Notes 
Dataset filtered to remove alignment and bias; model trained to be compliant. Read the related blog post on uncensored models.
Training Details 
Data Sources:
GPT4 and other models
Methodology:
FFT on parameters selected by Laser Scanner, using ChatML prompt template format.
Context Length:
8192
Hardware Used:
8xH100 node by Crusoe Cloud
Input Output 
Input Format:
ChatML
LLM NameDolphin 2.9.1 Qwen 110B
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-2.9.1-qwen-110b 
Base Model(s)  Qwen/Qwen1.5-110B   Qwen/Qwen1.5-110B
Model Size110b
Required VRAM193.4 GB
Updated2024-12-26
Maintainercognitivecomputations
Model Typeqwen2
Model Files  4.4 GB: 1-of-49   4.6 GB: 2-of-49   4.6 GB: 3-of-49   4.3 GB: 4-of-49   4.6 GB: 5-of-49   4.6 GB: 6-of-49   4.3 GB: 7-of-49   4.6 GB: 8-of-49   4.6 GB: 9-of-49   4.3 GB: 10-of-49   4.6 GB: 11-of-49   4.6 GB: 12-of-49   4.3 GB: 13-of-49   4.6 GB: 14-of-49   4.6 GB: 15-of-49   4.3 GB: 16-of-49   4.6 GB: 17-of-49   4.6 GB: 18-of-49   4.3 GB: 19-of-49   4.6 GB: 20-of-49   4.6 GB: 21-of-49   4.3 GB: 22-of-49   4.6 GB: 23-of-49   4.6 GB: 24-of-49   4.3 GB: 25-of-49   4.6 GB: 26-of-49   4.6 GB: 27-of-49   4.3 GB: 28-of-49   4.6 GB: 29-of-49   4.6 GB: 30-of-49   4.3 GB: 31-of-49   4.6 GB: 32-of-49   4.6 GB: 33-of-49   4.3 GB: 34-of-49   4.6 GB: 35-of-49   4.6 GB: 36-of-49   4.3 GB: 37-of-49   4.6 GB: 38-of-49   4.6 GB: 39-of-49   4.3 GB: 40-of-49   4.6 GB: 41-of-49   4.6 GB: 42-of-49   4.3 GB: 43-of-49
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.40.0.dev0
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to Dolphin 2.9.1 Qwen 110B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen1.5 110B Chat32K / 158.3 GB6356123
Qwen1.5 110B32K / 221.7 GB311193
Airoboros 110B 3.332K / 158.3 GB3582
Airoboros DPO 110B 3.332K / 158.3 GB270
Aqua Qwen 0.1 110B32K / 198.3 GB170
...wen 1.5 110B Layer Mix Bpw 2.28K / 40.7 GB171
Qwen1.5 110B Chat 4bit32K / 62.2 GB115
Qwen1.5 110B Chat 8bit32K / 179.8 GB141
...n1.5 110B Chat 3.35bpw H6 EXL232K / 49 GB121
...n1.5 110B Chat 3.25bpw H6 EXL232K / 47.7 GB111
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.9.1-qwen-110b.

Rank the Dolphin 2.9.1 Qwen 110B 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? 40303 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