Dolphin 2.9.3 Yi 1.5 34B 32K by cognitivecomputations

 ยป  All LLMs  ยป  cognitivecomputations  ยป  Dolphin 2.9.3 Yi 1.5 34B 32K   URL Share it on

  Autotrain compatible   Axolotl   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   Llama   Pytorch   Region:us   Sharded

Dolphin 2.9.3 Yi 1.5 34B 32K Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Dolphin 2.9.3 Yi 1.5 34B 32K Parameters and Internals

Model Type
LlamaForCausalLM
Use Cases
Considerations:The model is highly compliant with requests, including unethical ones. Users should exercise caution and implement necessary alignment measures.
Additional NotesDolphin is licensed according to the Apache 2.0 license. Users are responsible for content created using this model. Enjoy responsibly.
Training Details
Data Sources:
cognitivecomputations/Dolphin-2.9, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, microsoft/orca-math-word-problems-200k, Locutusque/function-calling-chatml, internlm/Agent-FLAN
Methodology:Finetuning with 8192 sequence length, using ChatML prompt template format.
Context Length:8192
Input Output
Input Format:ChatML prompt template format.
LLM NameDolphin 2.9.3 Yi 1.5 34B 32K
Repository ๐Ÿค—https://huggingface.co/cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k 
Base Model(s)  01-ai/Yi-1.5-34B-32k   01-ai/Yi-1.5-34B-32k
Model Size34b
Required VRAM69.2 GB
Updated2024-11-09
Maintainercognitivecomputations
Model Typellama
Model Files  4.8 GB: 1-of-15   4.8 GB: 2-of-15   5.0 GB: 3-of-15   4.8 GB: 4-of-15   4.8 GB: 5-of-15   5.0 GB: 6-of-15   4.8 GB: 7-of-15   4.8 GB: 8-of-15   5.0 GB: 9-of-15   4.8 GB: 10-of-15   4.8 GB: 11-of-15   5.0 GB: 12-of-15   4.8 GB: 13-of-15   4.8 GB: 14-of-15   1.2 GB: 15-of-15
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16
Dolphin 2.9.3 Yi 1.5 34B 32K (cognitivecomputations/dolphin-2.9.3-Yi-1.5-34B-32k)

Best Alternatives to Dolphin 2.9.3 Yi 1.5 34B 32K

Best Alternatives
Context / RAM
Downloads
Likes
34B Beta195K / 69.2 GB364862
Yi 34B 200K195K / 68.9 GB5214317
Bagel 34B V0.2195K / 68.7 GB951439
Bagel Hermes 34B Slerp195K / 68.9 GB39591
Smaug 34B V0.1195K / 69.2 GB320860
Yi 34B 200K AEZAKMI V2195K / 69.2 GB120112
Smaug 34B V0.1 ExPO195K / 69.2 GB28160
Mergekit Slerp Anaazls195K / 69.2 GB360
Faro Yi 34B195K / 69.2 GB35766
Bagel DPO 34B V0.5195K / 68.7 GB284217

Rank the Dolphin 2.9.3 Yi 1.5 34B 32K 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  

What open-source LLMs or SLMs are you in search of? 37727 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110