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

Dolphin 2.2 Yi 34B 200K by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Dolphin 2.2 Yi 34B 200K   URL Share it on

  933   

Dolphin 2.2 Yi 34B 200K is an open-source language model by cognitivecomputations. Features: 34b LLM, VRAM: 69.2GB, Context: 195K, License: apache-2.0, Instruction-Based, Merged, LLM Explorer Score: 0.14, Arc: 42.1, HellaSwag: 68.1, MMLU: 55.4, GSM8K: 3.1.

  Merged Model   Autotrain compatible   Conversational   Dataset:ehartford/dolphin Dataset:ehartford/samantha-dat... Dataset:ehartford/wizardlm evo... Dataset:jondurbin/airoboros-2....   En   Endpoints compatible   Instruct   Llama   Model-index   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.2-yi-34b-200k 

Dolphin 2.2 Yi 34B 200K Benchmarks

LLME Score: 0.14314
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 Yi 34B 200K (cognitivecomputations/dolphin-2.2-yi-34b-200k)

Dolphin 2.2 Yi 34B 200K Parameters and Internals

Model Type 
text generation
Use Cases 
Considerations:
Model is uncensored; it is compliant to requests, including unethical ones, without an external alignment layer.
Additional Notes 
Model trained for empathy and multi-turn conversation using curated datasets.
Training Details 
Data Sources:
ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/samantha-data, ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
Data Volume:
Dolphin, Airoboros dataset, Samantha, WizardLM
Methodology:
Fine-tuning using qLoRA and Axolotl
Context Length:
200000
Training Time:
3 days over 3 epochs
Hardware Used:
4x A100s
Model Architecture:
Based on Yi, uses ChatML prompt format
Responsible Ai Considerations 
Accountability:
User is responsible for any content generated using this model.
Mitigation Strategies:
Implement own alignment layer before deploying as a service
Input Output 
Input Format:
ChatML prompt format
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
2.2
Notes:
Enhancements in conversation and empathy, improved compliance, trained with curated Samantha and WizardLM data for multi-turn conversation.
LLM NameDolphin 2.2 Yi 34B 200K
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-2.2-yi-34b-200k 
Merged ModelYes
Model Size34b
Required VRAM69.2 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typellama
Instruction-BasedYes
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
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length200000
Model Max Length200000
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16

Best Alternatives to Dolphin 2.2 Yi 34B 200K

Best Alternatives
Context / RAM
Downloads
Likes
Bagel DPO 34B V0.5195K / 68.7 GB804017
Bagel 34B V0.5195K / 68.7 GB88
Bagel 34B V0.4195K / 68.7 GB1210
Dolphin 2.2 Yi 34B 200K195K / 69.2 GB1836
...gpt 32K Codellama 34B Instruct32K / 67.5 GB562
CodeLlama 34B Instruct Hf16K / 67.5 GB57493304
CodeLlama 34B Instruct Hf16K / 1.4 GB53
Speechless Codellama 34B V2.016K / 67.5 GB9617
CodeLlama 34B Instruct Hf16K / 67.5 GB47619
Speechless Codellama 34B V1.916K / 67.5 GB2860
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.2-yi-34b-200k.

Rank the Dolphin 2.2 Yi 34B 200K 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? 55558 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer