deepseek-coder-33b-instruct
by deepseek-ai
deepseek-coder-33b-instruct is an open-source AI model by deepseek-ai
Technical Specifications
View Config (3 entries)
{
"architectures": [
"LlamaForCausalLM"
],
"model_type": "llama",
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<ο½beginβofβsentenceο½>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<|EOT|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<ο½endβofβsentenceο½>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null,
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}"
}
}
Est. VRAM Required
~23 GB
Estimation Formula
VRAM = params Γ 0.6 + 2 GB
Based on FP16 precision.
β οΈ Does not account for KV cache or parallel overhead.
π Estimate only. Actual requirements may vary.
Based on open-source metadata snapshot. Last synced: Dec 31, 2025
π§ Architecture Explorer
Neural network architecture
Technical Specifications
View Config (3 entries)
{
"architectures": [
"LlamaForCausalLM"
],
"model_type": "llama",
"tokenizer_config": {
"bos_token": {
"__type": "AddedToken",
"content": "<ο½beginβofβsentenceο½>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<|EOT|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"__type": "AddedToken",
"content": "<ο½endβofβsentenceο½>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": null,
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}"
}
}
π Limitations & Considerations
- β’ Benchmark scores may vary based on evaluation methodology and hardware configuration.
- β’ VRAM requirements are estimates; actual usage depends on quantization and batch size.
- β’ FNI scores are relative rankings and may change as new models are added.
- β License Unknown: Verify licensing terms before commercial use.
- β’ Source: Huggingface
π Related Resources
π Related Papers
No related papers linked yet. Check the model's official documentation for research papers.
π Training Datasets
Training data information not available. Refer to the original model card for details.
π Related Models
Data unavailable