Dolphin 2.9.2 Qwen72b 8.0bpw H8 EXL2 by atcsecure

 ยป  All LLMs  ยป  atcsecure  ยป  Dolphin 2.9.2 Qwen72b 8.0bpw H8 EXL2   URL Share it on

  8-bit   Autotrain compatible   Axolotl   Base model:qwen/qwen2-72b   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   Exl2   Generated from trainer   License:other   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Rank the Dolphin 2.9.2 Qwen72b 8.0bpw H8 EXL2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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  
Dolphin 2.9.2 Qwen72b 8.0bpw H8 EXL2 (atcsecure/dolphin-2.9.2-qwen72b-8.0bpw-h8-exl2)

Best Alternatives to Dolphin 2.9.2 Qwen72b 8.0bpw H8 EXL2

Best Alternatives
HF Rank
Liberated Qwen1.5 72B74.1132K / 144.5 GB236681
Qwen1.5 72B72.9132K / 144.6 GB988557
Qwen1.5 72B Chat65.9632K / 144.6 GB35302214
Liberated Qwen1.5 72B 4bit6532K / 42.6 GB580
Liberated Qwen1.5 72B GGUF6532K / 28.5 GB2560
Liberated Qwen1.5 72B AWQ6532K / 41.3 GB411
Qwen1.5 72B Chat 4bit57.832K / 42.6 GB52
Qwen1.5 72B Chat AWQ57.832K / 41.3 GB99223
Qwen1.5 72B Chat GPTQ57.832K / 45.4 GB12
...Qwen2 72B 4 0bpw H6 EXL2 Pippa128K / 38.6 GB111
Note: green Score (e.g. "73.2") means that the model is better than atcsecure/dolphin-2.9.2-qwen72b-8.0bpw-h8-exl2.

Dolphin 2.9.2 Qwen72b 8.0bpw H8 EXL2 Parameters and Internals

LLM NameDolphin 2.9.2 Qwen72b 8.0bpw H8 EXL2
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Qwen2 72B   Qwen/Qwen2-72B
Model Size72b
Required VRAM66.8 GB
Model Typeqwen2
Model Files  8.5 GB: 1-of-8   8.6 GB: 2-of-8   8.6 GB: 3-of-8   8.5 GB: 4-of-8   8.5 GB: 5-of-8   8.5 GB: 6-of-8   8.6 GB: 7-of-8   7.0 GB: 8-of-8
Quantization Typeexl2
Model ArchitectureQwen2ForCausalLM
Context Length131072
Model Max Length131072
Transformers Version4.40.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 34944 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801