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 Llama 3 8B 8.0bpw H8 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Dolphin 2.9.1 Llama 3 8B 8.0bpw H8 EXL2   URL Share it on

  9   
  8-bit   Autotrain compatible   Axolotl Base model:meta-llama/meta-lla... Base model:quantized:meta-llam...   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   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/dolphin-2.9.1-llama-3-8b-8.0bpw-h8-exl2 

Dolphin 2.9.1 Llama 3 8B 8.0bpw H8 EXL2 Benchmarks

LLME Score: 0.18508
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 Llama 3 8B 8.0bpw H8 EXL2 (LoneStriker/dolphin-2.9.1-llama-3-8b-8.0bpw-h8-exl2)

Dolphin 2.9.1 Llama 3 8B 8.0bpw H8 EXL2 Parameters and Internals

Model Type 
AutoModelForCausalLM
Use Cases 
Primary Use Cases:
instruction, conversational, and coding skills, support function calling
Limitations:
May be highly compliant with unethical requests.
Considerations:
Advised to implement own alignment layer before use.
Additional Notes 
Trained on data generated from GPT4 and others. Model is more compliant, advised to implement your own alignment layer before service use. This model is uncensored and may comply with unethical requests. You are responsible for any content created.
Training Details 
Data Sources:
/workspace/datasets/dolphin-2.9/dolphin201-sharegpt2.jsonl, /workspace/datasets/dolphin-2.9/dolphin-coder-translate-sharegpt2.jsonl, /workspace/datasets/dolphin-2.9/dolphin-coder-codegen-sharegpt2.jsonl, /workspace/datasets/dolphin-2.9/m-a-p_Code-Feedback-sharegpt-unfiltered.jsonl, /workspace/datasets/dolphin-2.9/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt-unfiltered.jsonl, /workspace/datasets/dolphin-2.9/not_samantha_norefusals.jsonl, /workspace/datasets/dolphin-2.9/Orca-Math-resort-unfiltered.jsonl, /workspace/datasets/dolphin-2.9/agent_instruct_react_unfiltered.jsonl, /workspace/datasets/dolphin-2.9/toolbench_instruct_j1s1_3k_unfiltered.jsonl, /workspace/datasets/dolphin-2.9/toolbench_negative_unfiltered.jsonl, /workspace/datasets/dolphin-2.9/toolbench_react_10p_unfiltered.jsonl, /workspace/datasets/dolphin-2.9/toolbench_tflan_cot_30p_unfiltered.jsonl, /workspace/datasets/dolphin-2.9/openhermes200k_unfiltered.jsonl
Methodology:
FFT on all parameters, using ChatML prompt template format
Context Length:
8000
Training Time:
1.5 days
Hardware Used:
8x L40S provided by Crusoe Cloud
Input Output 
Input Format:
ChatML prompt template format
LLM NameDolphin 2.9.1 Llama 3 8B 8.0bpw H8 EXL2
Repository 🤗https://huggingface.co/LoneStriker/dolphin-2.9.1-llama-3-8b-8.0bpw-h8-exl2 
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM8.5 GB
Updated2025-02-22
MaintainerLoneStriker
Model Typellama
Model Files  8.5 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128258
Torch Data Typebfloat16

Best Alternatives to Dolphin 2.9.1 Llama 3 8B 8.0bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB212
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB71
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB102
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB70
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1225
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB2817
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB83
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB51
Llama 3 8B Instruct 262K 2bit256K / 2.5 GB71
...B Instruct 262k V2 EXL2 6.0bpw256K / 6.7 GB111
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/dolphin-2.9.1-llama-3-8b-8.0bpw-h8-exl2.

Rank the Dolphin 2.9.1 Llama 3 8B 8.0bpw H8 EXL2 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? 43470 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