4-bit Autotrain compatible Base model:grimulkan/goliath-l... Base model:quantized:grimulkan... Fp16 Gptq Llama Quantized Region:us Safetensors Sharded Tensorflow
Goliath LongLORA 120B Rope8 32K Fp16 GPTQ 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)
Goliath LongLORA 120B Rope8 32K Fp16 GPTQ Parameters and Internals
| LLM Name | Goliath LongLORA 120B Rope8 32K Fp16 GPTQ |
| Repository 🤗 | https://huggingface.co/TheBloke/Goliath-longLORA-120b-rope8-32k-fp16-GPTQ |
| Model Name | Goliath LongLORA 120B Rope8 32K |
| Model Creator | Grimulkan |
| Base Model(s) | |
| Model Size | 120b |
| Required VRAM | 59.8 GB |
| Updated | 2024-09-16 |
| Maintainer | TheBloke |
| Model Type | llama |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | fp16|gptq |
| Model Architecture | LlamaForCausalLM |
| License | llama2 |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.37.0.dev0 |
| Tokenizer Class | LlamaTokenizer |
| Padding Token | <unk> |
| Vocabulary Size | 32000 |
| Torch Data Type | float16 |
Best Alternatives to Goliath LongLORA 120B Rope8 32K Fp16 GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MegaDolphin 120B GPTQ | 4K / 61.1 GB | 7 | 4 |
| DiscoLM 120B GPTQ | 4K / 59.8 GB | 25 | 3 |
| Koishi 120B Qlora Gptq | 4K / 9.9 GB | 6 | 1 |
| Goliath 120B GPTQ | 4K / 59.8 GB | 35 | 16 |
| Miquella 120B 3.0bpw H6 EXL2 | 31K / 44.8 GB | 4 | 10 |
| Miquella 120B 8.0bpw H8 EXL2 | 31K / 118.1 GB | 8 | 3 |
| Miquella 120B 4.0bpw H6 EXL2 | 31K / 59.4 GB | 5 | 2 |
| ...t 120B Cat A Llama EXL2 5.5bpw | 8K / 85.3 GB | 308 | 0 |
| ...t 120B Cat A Llama EXL2 4.5bpw | 8K / 70.3 GB | 1 | 1 |
| ...h LongLORA 120B Rope8 32K Fp16 | 4K / 235.4 GB | 6 | 7 |
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Goliath-longLORA-120b-rope8-32k-fp16-GPTQ .
Rank the Goliath LongLORA 120B Rope8 32K Fp16 GPTQ 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? 35941 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803