Model Card on HF 🤗: https://huggingface.co/ig1/deepseek-coder-7b-base-v1.5-awq
Deepseek Coder 7B Base V1.5 AWQ Parameters and Internals
| LLM Name | Deepseek Coder 7B Base V1.5 AWQ |
| Repository 🤗 | https://huggingface.co/ig1/deepseek-coder-7b-base-v1.5-awq |
| Base Model(s) | |
| Model Size | 7b |
| Required VRAM | 4.8 GB |
| Updated | 2024-07-04 |
| Maintainer | ig1 |
| Model Type | llama |
| Model Files | |
| AWQ Quantization | Yes |
| Quantization Type | awq |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.41.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 102400 |
| Torch Data Type | float16 |
Best Alternatives to Deepseek Coder 7B Base V1.5 AWQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...Llama 7B Python Hf W4 G128 AWQ | 16K / 3.9 GB | 2359 | 0 |
| CodeLlama 7B Instruct AWQ | 16K / 3.9 GB | 176 | 4 |
| CodeLlama 7B AWQ | 16K / 3.9 GB | 34 | 5 |
| CodeLlama 7B Python AWQ | 16K / 3.9 GB | 22 | 4 |
| ...ama 7B Instruct Hf W4 G128 AWQ | 16K / 3.9 GB | 22 | 0 |
| Llama 2 Coder 7B AWQ | 4K / 3.9 GB | 31 | 3 |
| CodeLlama 7B Java 16bit | 16K / 13.5 GB | 17 | 0 |
| Codellama 7B Bnb 4bit | 16K / 3.9 GB | 3316 | 2 |
| ...lama 7B Tofuagent Contpretrain | 16K / 13.5 GB | 28 | 0 |
| ...ruct Solidity Bnb 4bit Smashed | 16K / 4.2 GB | 14 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than ig1/deepseek-coder-7b-base-v1.5-awq .
Rank the Deepseek Coder 7B Base V1.5 AWQ 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217