๐Ÿง  Model

DeepSeek-Coder-V2-Lite-Instruct

by deepseek-ai

DeepSeek-Coder-V2-Lite-Instruct is an open-source AI model by deepseek-ai

๐Ÿ• Updated 12/31/2025
Compare This Model

Technical Specifications

Parameters15.71
ArchitectureDeepseekV2ForCausalLM
View Config (4 entries)

{
  "architectures": [
    "DeepseekV2ForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_deepseek.DeepseekV2Config",
    "AutoModel": "modeling_deepseek.DeepseekV2Model",
    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
  },
  "model_type": "deepseek_v2",
  "tokenizer_config": {
    "bos_token": {
      "__type": "AddedToken",
      "content": "<๏ฝœbeginโ–ofโ–sentence๏ฝœ>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false
    },
    "eos_token": {
      "__type": "AddedToken",
      "content": "<๏ฝœendโ–ofโ–sentence๏ฝœ>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false
    },
    "pad_token": {
      "__type": "AddedToken",
      "content": "<๏ฝœendโ–ofโ–sentence๏ฝœ>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false
    },
    "unk_token": null,
    "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
  }
}
        
๐Ÿ’พ

Est. VRAM Required

~12 GB

๐Ÿ“‹ Estimate only. Actual requirements may vary.

๐Ÿ”„ Daily sync (11:00 Beijing)

Based on open-source metadata snapshot. Last synced: Dec 31, 2025

๐Ÿ“Š FNI Methodology ๐Ÿ“š Knowledge Baseโ„น๏ธ Verify with original source

๐Ÿง  Architecture Explorer

Neural network architecture

1 Input Layer
2 Hidden Layers
3 Attention
4 Output Layer
Parameters 15.71B

Technical Specifications

Parameters15.71
ArchitectureDeepseekV2ForCausalLM
0
View Config (4 entries)

{
  "architectures": [
    "DeepseekV2ForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "configuration_deepseek.DeepseekV2Config",
    "AutoModel": "modeling_deepseek.DeepseekV2Model",
    "AutoModelForCausalLM": "modeling_deepseek.DeepseekV2ForCausalLM"
  },
  "model_type": "deepseek_v2",
  "tokenizer_config": {
    "bos_token": {
      "__type": "AddedToken",
      "content": "<๏ฝœbeginโ–ofโ–sentence๏ฝœ>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false
    },
    "eos_token": {
      "__type": "AddedToken",
      "content": "<๏ฝœendโ–ofโ–sentence๏ฝœ>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false
    },
    "pad_token": {
      "__type": "AddedToken",
      "content": "<๏ฝœendโ–ofโ–sentence๏ฝœ>",
      "lstrip": false,
      "normalized": true,
      "rstrip": false,
      "single_word": false
    },
    "unk_token": null,
    "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}"
  }
}
        

๐Ÿ“ Limitations & Considerations

  • โ€ข Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • โ€ข VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • โ€ข FNI scores are relative rankings and may change as new models are added.
  • โš  License Unknown: Verify licensing terms before commercial use.
  • โ€ข Source: Huggingface

๐Ÿ“š Related Resources

๐Ÿ“„ Related Papers

No related papers linked yet. Check the model's official documentation for research papers.

๐Ÿ“Š Training Datasets

Training data information not available. Refer to the original model card for details.

๐Ÿ”— Related Models

Data unavailable

๐Ÿš€ What's Next?