Autotrain compatible Base model:finetune:unsloth/de... Base model:unsloth/deepseek-r1... Conversational En Endpoints compatible Finetuned Lora Qwen2 Region:us Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/mathdong01/DeepSeek-R1-14B-Finetuned
DeepSeek R1 14B Finetuned 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 R1 14B Finetuned Parameters and Internals
| LLM Name | DeepSeek R1 14B Finetuned |
| Repository 🤗 | https://huggingface.co/mathdong01/DeepSeek-R1-14B-Finetuned |
| Base Model(s) | |
| Model Size | 14b |
| Required VRAM | 29.7 GB |
| Updated | 2025-08-10 |
| Maintainer | mathdong01 |
| Model Files | |
| Supported Languages | en |
| Model Architecture | AutoModelForCausalLM |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <|vision_pad|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|o_proj|q_proj|k_proj|gate_proj|up_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to DeepSeek R1 14B Finetuned
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MING MoE 14B | 0K / 0.1 GB | 8 | 0 |
| Phi3 14B Unsloth Sft Quip 3bit | 0K / 0.1 GB | 5 | 0 |
| Phi3 14B Unsloth Sft Quip 2bit | 0K / 0.1 GB | 5 | 0 |
| ReWiz Qwen 2.5 14B | 0K / 29.7 GB | 776 | 5 |
Note: green Score (e.g. "73.2") means that the model is better than mathdong01/DeepSeek-R1-14B-Finetuned .
Rank the DeepSeek R1 14B Finetuned 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? 51544 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124