Adapter Base model:adapter:deepseek-ai... Base model:deepseek-ai/deepsee... Conversational En Finetuned Lora Peft Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/Vijayendra/DeepSeek-Qwen2.5-14B-DeepThinker-v2
DeepSeek Qwen2.5 14B DeepThinker V2 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 14B DeepThinker V2 Parameters and Internals
| LLM Name | DeepSeek Qwen2.5 14B DeepThinker V2 |
| Repository 🤗 | https://huggingface.co/Vijayendra/DeepSeek-Qwen2.5-14B-DeepThinker-v2 |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 0.3 GB |
| Updated | 2025-07-29 |
| Maintainer | Vijayendra |
| Model Files | |
| Supported Languages | en |
| Model Architecture | Adapter |
| License | mit |
| Model Max Length | 16384 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | self_attn.o_proj|mlp.down_proj|self_attn.q_proj|self_attn.k_proj|self_attn.v_proj|mlp.gate_proj|mlp.up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Best Alternatives to DeepSeek Qwen2.5 14B DeepThinker V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Qwen Story Test Qlora | 0K / 1.1 GB | 33 | 1 |
| Vaivcon2 | 0K / 0.2 GB | 5 | 0 |
| Qwen Nampdn Ai Tiny Textbooks | 0K / 0.2 GB | 0 | 1 |
| Careqwen 14B Chat Sft Multi | 0K / 0 GB | 5 | 1 |
Rank the DeepSeek Qwen2.5 14B DeepThinker V2 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? 50230 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124