Autotrain compatible Codegen Conversational Endpoints compatible Exl2 Llama Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/DeepMagic-Coder-7b-8.0bpw-h8-exl2
DeepMagic Coder 7B 8.0bpw H8 EXL2 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)
DeepMagic Coder 7B 8.0bpw H8 EXL2 Parameters and Internals
| Training Details |
|
| LLM Name | DeepMagic Coder 7B 8.0bpw H8 EXL2 |
| Repository 🤗 | https://huggingface.co/LoneStriker/DeepMagic-Coder-7b-8.0bpw-h8-exl2 |
| Model Size | 7b |
| Required VRAM | 6.9 GB |
| Updated | 2024-12-22 |
| Maintainer | LoneStriker |
| Model Type | llama |
| Model Files | |
| Quantization Type | exl2 |
| Generates Code | Yes |
| Model Architecture | LlamaForCausalLM |
| License | other |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <｜end▁of▁sentence｜> |
| Vocabulary Size | 32256 |
| Torch Data Type | float16 |
Best Alternatives to DeepMagic Coder 7B 8.0bpw H8 EXL2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| 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 |
| ...B Instruct Hf Bnb 4bit Smashed | 16K / 4.2 GB | 21 | 0 |
| CodeLlama 7B Python Onnx Fp16 | 16K / GB | 10 | 1 |
| CodeLlama 7B Python 4bit MLX | 16K / 4 GB | 47 | 14 |
| CodelLama7B Inst DPO 7K Mlx | 16K / 4.2 GB | 8 | 2 |
| ...eLlama 7B Instruct Hf 4bit MLX | 16K / 4.2 GB | 12 | 1 |
| CodeLlama 7B Fp16 | 16K / 13.5 GB | 3226 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/DeepMagic-Coder-7b-8.0bpw-h8-exl2 .
Rank the DeepMagic Coder 7B 8.0bpw H8 EXL2 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