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

Qwen2 1.5B Merged 4bit Forced by inflaton

 »  All LLMs  »  inflaton  »  Qwen2 1.5B Merged 4bit Forced   URL Share it on

  11   
  Merged Model   Arxiv:1910.09700   4-bit   4bit   Autotrain compatible   Bitsandbytes   Conversational   Endpoints compatible   Quantized   Qwen2   Region:us   Safetensors   Sft   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/inflaton/Qwen2-1.5B-merged_4bit_forced 

Qwen2 1.5B Merged 4bit Forced Benchmarks

LLME Score: 0.19215
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 1.5B Merged 4bit Forced (inflaton/Qwen2-1.5B-merged_4bit_forced)

Qwen2 1.5B Merged 4bit Forced Parameters and Internals

LLM NameQwen2 1.5B Merged 4bit Forced
Repository 🤗https://huggingface.co/inflaton/Qwen2-1.5B-merged_4bit_forced 
Merged ModelYes
Model Size1.5b
Required VRAM1.1 GB
Updated2024-12-06
Maintainerinflaton
Model Typeqwen2
Model Files  1.1 GB
Quantization Type4bit
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.40.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2 1.5B Merged 4bit Forced

Model
Likes
Downloads
VRAM
Qwen2 1.5B MAC Gguf Q8 00230 GB
Qwen2 1.5B MAC Gguf Q4 K M0220 GB
Qwen2 1.5B MAC Gguf F160173 GB
...n2 1.5B MAC Merged 4bit Forced091 GB
Qwen2 1.5B MAC Gguf Q5 K M050 GB

Best Alternatives to Qwen2 1.5B Merged 4bit Forced

Best Alternatives
Context / RAM
Downloads
Likes
... R1 Distill Qwen 1.5B Bnb 4bit128K / 1.6 GB1214376
...ill Qwen 1.5B Unsloth Bnb 4bit128K / 1.8 GB6564512
DeepSeek R1 ForumNXT128K / 3.5 GB370
Deep Ft5 Grp 16bit128K / 3.5 GB730
Atlas Flash 1.5B Preview128K / 3.5 GB1062
Model128K / 3.5 GB120
Qwen2 1.5B Bnb 4bit128K / 1.1 GB76316
IcaroLM128K / 3.1 GB1312
Qwen2 1.5B 4bit128K / 0.9 GB200
...1.5B Instruct Unsloth Bnb 4bit32K / 1.5 GB189232
Note: green Score (e.g. "73.2") means that the model is better than inflaton/Qwen2-1.5B-merged_4bit_forced.

Rank the Qwen2 1.5B Merged 4bit Forced 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