Autotrain compatible Endpoints compatible Exl2 Llama Quantized Region:us Safetensors Sharded Tensorflow
Goliath120B EXL2 2 2.64bpw Parameters and Internals
| LLM Name | Goliath120B EXL2 2 2.64bpw |
| Repository | Open on 🤗 |
| Model Size | 120b |
| Required VRAM | 39.5 GB |
| Updated | 2024-07-26 |
| Maintainer | LavaPlanet |
| Model Type | llama |
| Model Files | |
| Quantization Type | exl2 |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.35.0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Goliath120B EXL2 2 2.64bpw
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| Miquella 120B 3.0bpw H6 EXL2 | 0.2 | 31K / 44.8 GB | 6 | 10 |
| Miquella 120B 8.0bpw H8 EXL2 | 0.2 | 31K / 118.1 GB | 7 | 3 |
| Miquella 120B 4.0bpw H6 EXL2 | 0.2 | 31K / 59.4 GB | 6 | 2 |
| ...t 120B Cat A Llama EXL2 5.5bpw | 0.2 | 8K / 85.3 GB | 130 | 0 |
| ...t 120B Cat A Llama EXL2 4.5bpw | 0.2 | 8K / 70.3 GB | 6 | 1 |
| ...h LongLORA 120B Rope8 32K Fp16 | 0.2 | 4K / 235.4 GB | 17 | 7 |
| ...RA 120B Rope8 32K 6bpw H8 EXL2 | 0.2 | 4K / 88.7 GB | 6 | 1 |
| ...egaDolphin 120B 2.9bpw H6 EXL2 | 0.2 | 4K / 44.3 GB | 14 | 3 |
| ...gaDolphin 120B 2.65bpw H6 EXL2 | 0.2 | 4K / 40.5 GB | 13 | 2 |
| ...egaDolphin 120B 4.0bpw H6 EXL2 | 0.2 | 4K / 60.8 GB | 14 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than LavaPlanet/Goliath120B-exl2_2-2.64bpw .
Rank the Goliath120B EXL2 2 2.64bpw 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? 34446 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072501