4bit Autotrain compatible Endpoints compatible Instruct Llama Lora Pytorch Quantized Region:us Sharded
Model Card on HF 🤗: https://huggingface.co/Enno-Ai/vigogne2-enno-13b-sft-lora-4bit
Vigogne2 Enno 13B Sft Lora 4bit Benchmarks
ARC: 62.03 vs 96.7 (so35)-35.9%
HellaSwag: 82.65 vs 95.3 (gpt4)-13.3%
MMLU: 54.11 vs 88.3 (so35)-38.7%
TruthfulQA: 42.98 vs 59 (gpt4)-27.2%
WinoGrande: 76.95 vs 87.5 (gpt4)-12.1%
GSM8K: 0.15 vs 96.4 (so35)-99.8%
LLME Score: 0.16463
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)
Vigogne2 Enno 13B Sft Lora 4bit Parameters and Internals
| LLM Name | Vigogne2 Enno 13B Sft Lora 4bit |
| Repository 🤗 | https://huggingface.co/Enno-Ai/vigogne2-enno-13b-sft-lora-4bit |
| Model Size | 13b |
| Required VRAM | 26 GB |
| Updated | 2024-12-04 |
| Maintainer | Enno-Ai |
| Model Type | llama |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | LlamaForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.33.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Beginning of Sentence Token | <s> |
| End of Sentence Token | </s> |
| Unk Token | <unk> |
| Vocabulary Size | 32000 |
| LoRA Model | Yes |
| Torch Data Type | float16 |
Best Alternatives to Vigogne2 Enno 13B Sft Lora 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| CodeLlama 13B Instruct Fp16 | 16K / 26 GB | 3484 | 28 |
| ...Llama 13B Instruct Hf 4bit MLX | 16K / 7.8 GB | 100 | 2 |
| ...13B Instruct Nf4 Fp16 Upscaled | 16K / 26 GB | 130 | 0 |
| ...B Fast Instruct 4bit Quantized | 4K / 7.8 GB | 76 | 0 |
| Model 007 13b V2 | 4K / 26 GB | 26 | 4 |
| Xwin LM 13B V0.2 EXL2 | 4K / 5.2 GB | 20 | 3 |
| Mythalion 13B 2.30bpw H4 EXL2 | 4K / 4.1 GB | 13 | 3 |
| ...lion Kimiko V2.6.05bpw H8 EXL2 | 4K / 10.1 GB | 7 | 1 |
| Law LLM 13B 4.0bpw H6 EXL2 | 2K / 6.8 GB | 5 | 1 |
| Finance LLM 13B 6.0bpw H6 EXL2 | 2K / 10 GB | 4 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than Enno-Ai/vigogne2-enno-13b-sft-lora-4bit .
Rank the Vigogne2 Enno 13B Sft Lora 4bit 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? 43470 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227