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

Firefly Qwen1.5 En 14B Alpha by YeungNLP

 »  All LLMs  »  YeungNLP  »  Firefly Qwen1.5 En 14B Alpha   URL Share it on

  21   
  Autotrain compatible   Conversational   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/YeungNLP/firefly-qwen1.5-en-14b-alpha 

Firefly Qwen1.5 En 14B Alpha Benchmarks

ARC: 57.59 vs 96.7 (so35)-40.4%
HellaSwag: 80.92 vs 95.3 (gpt4)-15.1%
MMLU: 67.57 vs 88.3 (so35)-23.5%
TruthfulQA: 55.36 vs 59 (gpt4)-6.2%
WinoGrande: 71.74 vs 87.5 (gpt4)-18%
GSM8K: 64.97 vs 96.4 (so35)-32.6%
LLME Score: 0.20022
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Firefly Qwen1.5 En 14B Alpha (YeungNLP/firefly-qwen1.5-en-14b-alpha)

Firefly Qwen1.5 En 14B Alpha Parameters and Internals

Model Type 
language model, text generation
Use Cases 
Areas:
research, experimentation
Primary Use Cases:
chatbots, Q&A
Limitations:
not optimized for multi-turn tasks
Considerations:
Limited training length may affect performance.
Additional Notes 
This model is a preview version and subject to further updates.
Supported Languages 
English (Trained), Chinese (Untested)
Training Details 
Data Sources:
English
Methodology:
QLoRA
Context Length:
1024
Input Output 
Input Format:
List of messages with role and content.
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use lower temperature and top-p for more deterministic responses.
LLM NameFirefly Qwen1.5 En 14B Alpha
Repository 🤗https://huggingface.co/YeungNLP/firefly-qwen1.5-en-14b-alpha 
Model Size14b
Required VRAM28.4 GB
Updated2025-02-22
MaintainerYeungNLP
Model Typeqwen2
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   5.0 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   3.5 GB: 6-of-6
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Firefly Qwen1.5 En 14B Alpha

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 14B Instruct 1M986K / 29.6 GB35169254
Qwen2.5 14B DeepSeek R1 1M986K / 29.7 GB120311
...14B Instruct 1M GRPO Reasoning986K / 29.7 GB2043
Impish QWEN 14B 1M986K / 29.7 GB12711
Calcium Opus 14B Elite 1M986K / 29.7 GB7110
ZYH LLM Qwen2.5 14B V2986K / 29.7 GB561
Q2.5 14B Instruct 1M Harmony986K / 29.7 GB361
Qwen2.5 14B Instruct 1M986K / 29.7 GB3213
...wen2.5 14B Instruct 1M Unalign986K / 29.7 GB3120
Qwen2.5 14B 1M Unalign V2986K / 29.7 GB300
Note: green Score (e.g. "73.2") means that the model is better than YeungNLP/firefly-qwen1.5-en-14b-alpha.

Rank the Firefly Qwen1.5 En 14B Alpha 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