4-bit Autotrain compatible Base model:deepseek-ai/deepsee... Base model:quantized:deepseek-... Codegen Conversational Gptq Instruct Llama Quantized Region:us Safetensors
Deepseek Coder 33B Instruct GPTQ 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 Coder 33B Instruct GPTQ Parameters and Internals
| LLM Name | Deepseek Coder 33B Instruct GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/deepseek-coder-33B-instruct-GPTQ |
| Model Name | Deepseek Coder 33B Instruct |
| Model Creator | DeepSeek |
| Base Model(s) | |
| Model Size | 33b |
| Required VRAM | 17.4 GB |
| Updated | 2024-10-18 |
| Maintainer | TheBloke |
| Model Type | deepseek |
| Instruction-Based | Yes |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | LlamaTokenizerFast |
| Beginning of Sentence Token | <｜begin▁of▁sentence｜> |
| End of Sentence Token | <|EOT|> |
| Vocabulary Size | 32256 |
| Torch Data Type | bfloat16 |
Best Alternatives to Deepseek Coder 33B Instruct GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...er 33B Instruct 4.0bpw H6 EXL2 | 16K / 17.1 GB | 4 | 5 |
| ...er 33B Instruct 8.0bpw H8 EXL2 | 16K / 33.6 GB | 2 | 3 |
| ...r 33B Instruct 4.65bpw H6 EXL2 | 16K / 19.8 GB | 10 | 1 |
| ...er 33B Instruct 5.0bpw H6 EXL2 | 16K / 21.2 GB | 5 | 1 |
| ...er 33B Instruct 3.0bpw H6 EXL2 | 16K / 13 GB | 3 | 1 |
| Deepseek Wizard 33B Slerp | 16K / 35.3 GB | 9 | 0 |
| Deepseek Coder 33B Instruct | 16K / 66.5 GB | 6507 | 451 |
| ValidateAI 2 33B AT | 16K / 66.5 GB | 13 | 0 |
| ValidateAI 3 33B Ties | 16K / 66.5 GB | 7 | 0 |
| ...eepseek Coder 33B Instruct AWQ | 16K / 18.1 GB | 69511 | 35 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-coder-33B-instruct-GPTQ .
Rank the Deepseek Coder 33B Instruct GPTQ 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? 36966 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803