Llama 3 Soliloquy 8B V2 GPTQ Benchmarks
ARC: 58.96 vs 96.7 (so35)-39%
HellaSwag: 80.11 vs 95.3 (gpt4)-15.9%
MMLU: 64.73 vs 88.3 (so35)-26.7%
TruthfulQA: 51.61 vs 59 (gpt4)-12.5%
WinoGrande: 75.93 vs 87.5 (gpt4)-13.2%
GSM8K: 58.76 vs 96.4 (so35)-39%
LLME Score: 0.2323
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)
Llama 3 Soliloquy 8B V2 GPTQ Parameters and Internals
| LLM Name | Llama 3 Soliloquy 8B V2 GPTQ |
| Repository 🤗 | https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v2-GPTQ |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 5.7 GB |
| Updated | 2024-09-03 |
| Maintainer | openlynn |
| Model Type | llama |
| Model Files | |
| GPTQ Quantization | Yes |
| Quantization Type | gptq|4bit |
| Model Architecture | LlamaForCausalLM |
| License | cc-by-nc-sa-4.0 |
| Context Length | 24576 |
| Model Max Length | 24576 |
| Transformers Version | 4.41.0.dev0 |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|end_of_text|> |
| Vocabulary Size | 128256 |
| Torch Data Type | float16 |
Best Alternatives to Llama 3 Soliloquy 8B V2 GPTQ
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...a 3 8B Instruct 262K 4bit GPTQ | 256K / 5.8 GB | 6 | 1 |
| ... 8B Instruct 262K 4bit GPTQ 02 | 256K / 5.7 GB | 5 | 0 |
| ...lama 3.1 8B Instruct GPTQ INT4 | 128K / 5.8 GB | 42823 | 8 |
| ...Instruct 80K Qlora Merged GPTQ | 80K / 5.8 GB | 37 | 0 |
| ...oLeo Instruct 8B 32K V0.1 GPTQ | 64K / 5.7 GB | 6 | 0 |
| Llama3 German 8B 32K GPTQ | 64K / 5.7 GB | 5 | 0 |
| Tsukasa Llama 3 8B Qlora Gptq | 32K / 5.8 GB | 6 | 0 |
| Llama 3 Soliloquy 8B GPTQ | 16K / 5.7 GB | 10 | 5 |
| Llama 3 8B Instruct GPTQ 8 Bit | 8K / 9.7 GB | 12341 | 24 |
| Llama 3 8B Instruct GPTQ 4 Bit | 8K / 5.7 GB | 2726 | 24 |
Note: green Score (e.g. "73.2") means that the model is better than openlynn/Llama-3-Soliloquy-8B-v2-GPTQ .
Rank the Llama 3 Soliloquy 8B V2 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? 35693 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803