Rombos LLM V2.5 Qwen 32B by rombodawg

 ยป  All LLMs  ยป  rombodawg  ยป  Rombos LLM V2.5 Qwen 32B   URL Share it on

  Merged Model   Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-32b-in...   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Rombos LLM V2.5 Qwen 32B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rombos LLM V2.5 Qwen 32B (rombodawg/Rombos-LLM-V2.5-Qwen-32b)

Rombos LLM V2.5 Qwen 32B Parameters and Internals

Additional Notes 
I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it.
Training Details 
Methodology:
The *Ties* merge method was used to merge the instruct model with the base model.
LLM NameRombos LLM V2.5 Qwen 32B
Repository ๐Ÿค—https://huggingface.co/rombodawg/Rombos-LLM-V2.5-Qwen-32b 
Base Model(s)  Qwen/Qwen2.5-32B-Instruct   Qwen/Qwen2.5-32B-Instruct
Merged ModelYes
Model Size32b
Required VRAM65.8 GB
Updated2025-02-08
Maintainerrombodawg
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-14   5.0 GB: 2-of-14   4.9 GB: 3-of-14   4.9 GB: 4-of-14   4.9 GB: 5-of-14   4.9 GB: 6-of-14   4.9 GB: 7-of-14   4.9 GB: 8-of-14   4.9 GB: 9-of-14   4.9 GB: 10-of-14   4.9 GB: 11-of-14   4.9 GB: 12-of-14   4.9 GB: 13-of-14   1.9 GB: 14-of-14
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Rombos LLM V2.5 Qwen 32B

Best Alternatives
Context / RAM
Downloads
Likes
...y Qwen2.5coder 32B V24.1q 200K195K / 65.8 GB62
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB3299
...wen2.5 32B Inst BaseMerge TIES128K / 65.8 GB131
Franqwenstein 35B128K / 69.8 GB2178
EVA Qwen2.5 32B V0.2128K / 65.8 GB333248
...1 Qwen2.5 Instruct 32B Preview128K / 65.8 GB1967
QwQenSeek Coder128K / 65.7 GB1094
Qwenstein2.5 32B Instruct128K / 65.5 GB1042
EVA Qwen2.5 32B V0.0128K / 65.8 GB110326
EVA Qwen2.5 32B V0.1128K / 65.8 GB105814

Rank the Rombos LLM V2.5 Qwen 32B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 42807 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227