Qwen2.5 Coder 7B Instruct Ties by Etherll

 ยป  All LLMs  ยป  Etherll  ยป  Qwen2.5 Coder 7B Instruct Ties   URL Share it on

  Merged Model   Arxiv:2306.01708   Autotrain compatible Base model:qwen/qwen2.5-coder-... Base model:qwen/qwen2.5-coder-...   Codegen   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow

Qwen2.5 Coder 7B Instruct Ties Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Qwen2.5 Coder 7B Instruct Ties Parameters and Internals

Additional Notes 
This model is a merge created using mergekit, with Qwen/Qwen2.5-Coder-7B as the base model and Qwen/Qwen2.5-Coder-7B-Instruct as part of the merged components. The merge method used is TIES, with specific configuration settings like normalize: true, int8_mask: true, and dtype: bfloat16.
LLM NameQwen2.5 Coder 7B Instruct Ties
Repository ๐Ÿค—https://huggingface.co/Etherll/Qwen2.5-Coder-7B-Instruct-Ties 
Base Model(s)  Qwen/Qwen2.5-Coder-7B-Instruct   Qwen/Qwen2.5-Coder-7B   Qwen/Qwen2.5-Coder-7B-Instruct   Qwen/Qwen2.5-Coder-7B
Merged ModelYes
Model Size7b
Required VRAM15.2 GB
Updated2024-11-21
MaintainerEtherll
Model Typeqwen2
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   0.3 GB: 4-of-4
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.44.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace
Qwen2.5 Coder 7B Instruct Ties (Etherll/Qwen2.5-Coder-7B-Instruct-Ties)

Best Alternatives to Qwen2.5 Coder 7B Instruct Ties

Best Alternatives
Context / RAM
Downloads
Likes
StockQwen 2.5 7B128K / 15.2 GB3842
Qwen2.5 Coder 7B Instruct32K / 15.2 GB114920318
...der 7B Chat Instruct TIES V1.232K / 15.4 GB791
Rombos Coder V2.5 Qwen 7B32K / 15.2 GB1153
Urd Qwen2.5 7B32K / 16.2 GB240
...en2 Coder7b Reflct Adamw Iter132K / 15.2 GB780
Qwen2.5 Coder 7B Instruct32K / 15.3 GB6274
Hammer2.0 7B32K / 15.2 GB3269
...Coder 7B 3x Instruct TIES V1.132K / 15.2 GB202
Qwen 2.5 7B TitanFusion V5 Exp32K / 15.2 GB250
Note: green Score (e.g. "73.2") means that the model is better than Etherll/Qwen2.5-Coder-7B-Instruct-Ties.

Rank the Qwen2.5 Coder 7B Instruct Ties 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? 38149 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110