Arxiv:1910.09700 Autotrain compatible Conversational Endpoints compatible Gguf Quantized Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/jan-hq/Deepseek-Qwen2.5-7B-Redistil
Deepseek Qwen2.5 7B Redistil Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Deepseek Qwen2.5 7B Redistil Parameters and Internals
| LLM Name | Deepseek Qwen2.5 7B Redistil |
| Repository 🤗 | https://huggingface.co/jan-hq/Deepseek-Qwen2.5-7B-Redistil |
| Model Size | 7b |
| Required VRAM | 15.2 GB |
| Updated | 2025-02-22 |
| Maintainer | jan-hq |
| Model Type | qwen2 |
| Model Files | |
| GGUF Quantization | Yes |
| Quantization Type | gguf |
| Model Architecture | Qwen2ForCausalLM |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.48.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Deepseek Qwen2.5 7B Redistil
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Pathumma Llm Text 1.0.0 | 128K / 30.5 GB | 451 | 8 |
| SvelteCodeQwen1.5 7B Chat | 64K / 14.5 GB | 460 | 0 |
| CodeQwen1.5 7B Chat GGUF | 64K / 3 GB | 132 | 2 |
| Qwen2 Cantonese 7B Instruct | 32K / 15.4 GB | 130 | 3 |
| Openthaigpt1.5 7B Instruct | 32K / 15.2 GB | 2053 | 15 |
| Qwen 2.5 7B Threatflux | 32K / 15.5 GB | 72 | 5 |
| ...der 7B Instruct Abliterated V1 | 32K / 15.2 GB | 53 | 1 |
| Qwen2 7B Instruct GGUF | 32K / 3 GB | 105 | 1 |
| Qwen2 7B Instruct GGUF | 32K / 3 GB | 99 | 0 |
| Qwen1.5 7B Chat GGUF | 32K / 3.1 GB | 123 | 1 |
Rank the Deepseek Qwen2.5 7B Redistil 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! 🌟
What open-source LLMs or SLMs are you in search of? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227