Merged Model Autotrain compatible Base model:mistralai/mistral-7... Conversational Endpoints compatible Exl2 License:apache-2.0 Llama Quantized Region:us Safetensors Sharded Tensorflow
Smaugv0.1 4.65bpw H6 EXL2 Benchmarks
Rank the Smaugv0.1 4.65bpw H6 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! 🌟
Best Alternatives to Smaugv0.1 4.65bpw H6 EXL2
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Smaugv0.1 3.0bpw H6 EXL2 | 60.1 | 195K / 13.9 GB | 1 | 1 |
| Smaugv0.1 4.0bpw H6 EXL2 | 60.1 | 195K / 18 GB | 1 | 1 |
| Smaugv0.1 5.0bpw H6 EXL2 | 60.1 | 195K / 22.3 GB | 1 | 3 |
| Smaugv0.1 6.0bpw H6 EXL2 | 60.1 | 195K / 26.4 GB | 1 | 4 |
| Smaugv0.1 8.0bpw H8 EXL2 | 60.1 | 195K / 34.9 GB | 1 | 1 |
| Smaugv0.1 AWQ | 60.1 | 195K / 19.3 GB | 1 | 1 |
| Vicuna 7B V1.5 | 55.27 | 4K / 13.5 GB | 455546 | 260 |
| ...p 0.05 Max Grad1.0 Grad Accu32 | 54.6 | 32K / 14.4 GB | 8 | 0 |
| Llama2 Chinese 7B Chat | 54.23 | 4K / 13.5 GB | 2814 | 213 |
| Vicuna 7B V1.5 16K | 54.02 | 4K / 13.5 GB | 6426 | 84 |
Smaugv0.1 4.65bpw H6 EXL2 Parameters and Internals
| LLM Name | Smaugv0.1 4.65bpw H6 EXL2 |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Merged Model | Yes |
| Model Size | 7b |
| Required VRAM | 20.8 GB |
| Updated | 2024-07-05 |
| Maintainer | LoneStriker |
| Model Type | llama |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | LlamaForCausalLM |
| License | apache-2.0 |
| Context Length | 200000 |
| Model Max Length | 200000 |
| Transformers Version | 4.36.2 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 64000 |
| Initializer Range | 0.02 |
| Torch Data Type | bfloat16 |
What open-source LLMs or SLMs are you in search of? 34431 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801