Arxiv:1910.09700 Adapter Base model:adapter:deepseek-ai... Base model:deepseek-ai/deepsee... Codegen Finetuned Instruct Lora Peft Region:us
Model Card on HF 🤗: https://huggingface.co/ByteForge/Deepseek_1.3b_instruct_adapter
Deepseek 1.3b Instruct Adapter 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 1.3B Instruct Adapter Parameters and Internals
| LLM Name | Deepseek 1.3b Instruct Adapter |
| Repository 🤗 | https://huggingface.co/ByteForge/Deepseek_1.3b_instruct_adapter |
| Base Model(s) | |
| Model Size | 1.3b |
| Required VRAM | 0.3 GB |
| Updated | 2025-03-19 |
| Maintainer | ByteForge |
| Instruction-Based | Yes |
| Model Files | |
| Generates Code | Yes |
| Model Architecture | Adapter |
| Model Max Length | 16384 |
| Is Biased | none |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <｜begin▁of▁sentence｜> |
| End of Sentence Token | <|EOT|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | gate_proj|q_proj|v_proj|down_proj|k_proj|lm_head|o_proj|up_proj |
| LoRA Alpha | 8 |
| LoRA Dropout | 0.05 |
| R Param | 16 |
Rank the Deepseek 1.3B Instruct Adapter 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? 47770 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227