LLM EXPLORER 61,491 MODELS INDEXED

Dolphin 2.2 Yi 34B 6.0bpw H6 EXL2 by LoneStriker

By LoneStriker · 2 downloads
HF Repo ↗ Copy URL

Dolphin 2.2 Yi 34B 6.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 34b LLM, VRAM: 26.4GB, Context: 16K, License: other, Quantized, Instruction-Based, Merged, LLM Explorer Score: 0.09.

  Merged Model   Dataset:ehartford/dolphin Dataset:ehartford/samantha-dat... Dataset:ehartford/wizardlm evo... Dataset:jondurbin/airoboros-2....   En   Endpoints compatible   Exl2   Instruct   Llama   Pytorch   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/dolphin-2.2-yi-34b-6.0bpw-h6-exl2 

Dolphin 2.2 Yi 34B 6.0bpw H6 EXL2 Parameters and Internals

Model Type 
Text Generation
Use Cases 
Areas:
Research, Commercial applications
Applications:
Multi-turn conversation, Personal advice generation
Primary Use Cases:
Empathy, Long conversations
Limitations:
Lacks alignment and bias control
Considerations:
Implement an alignment layer before exposing the model as a service.
Additional Notes 
New in 2.2: conversation and empathy features added with updates from Samantha and WizardLM data. Sponsorship by a16z. Uncensored model with an advising nature.
Supported Languages 
input (English), output (English)
Training Details 
Data Sources:
ehartford/dolphin, jondurbin/airoboros-2.2.1, ehartford/samantha-data, ehartford/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split
Methodology:
Modified dataset for uncensoring, deduping, cleaning, and quality. Additional datasets added for creativity and multi-turn conversation training
Training Time:
3 days
Hardware Used:
4x A100s
Input Output 
Input Format:
ChatML format
Accepted Modalities:
Text
Output Format:
Text
LLM NameDolphin 2.2 Yi 34B 6.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/dolphin-2.2-yi-34b-6.0bpw-h6-exl2 
Merged ModelYes
Model Size34b
Required VRAM26.4 GB
Updated2026-07-13
MaintainerLoneStriker
Model Typellama
Instruction-BasedYes
Model Files  8.6 GB: 1-of-4   8.5 GB: 2-of-4   8.6 GB: 3-of-4   0.7 GB: 4-of-4
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.34.1
Tokenizer ClassYiTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typefloat16

Best Alternatives to Dolphin 2.2 Yi 34B 6.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
....2 Yi 34B 200K 4.65bpw H6 EXL2195K / 20.8 GB42
...2.2 Yi 34B 200K 6.0bpw H6 EXL2195K / 26.5 GB31
CodeLlama 34B Instruct Fp1616K / 67.5 GB1317
CodeLlama 34B Instruct Hf 4bit16K / 19.4 GB632
...phin 2.2 Yi 34B 4.0bpw H6 EXL216K / 18 GB83
...phin 2.2 Yi 34B 8.0bpw H8 EXL216K / 34.8 GB73
...phin 2.2 Yi 34B 5.0bpw H6 EXL216K / 22.2 GB33
Bagel DPO 34B V0.5195K / 68.7 GB804017
Dolphin 2.2 Yi 34B 200K195K / 69.2 GB93336
Bagel 34B V0.5195K / 68.7 GB88
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/dolphin-2.2-yi-34b-6.0bpw-h6-exl2.