Adapter Base model:adapter:meta-llama/... Base model:meta-llama/meta-lla... Finetuned Generated from trainer Instruct Llama-factory Lora Peft Region:us Safetensors
Llama3 8b Sa V0.1 Benchmarks
ARC: 62.29 vs 96.7 (so35)-35.6%
HellaSwag: 79.26 vs 95.3 (gpt4)-16.8%
MMLU: 67.41 vs 88.3 (so35)-23.7%
TruthfulQA: 52.51 vs 59 (gpt4)-11%
WinoGrande: 76.48 vs 87.5 (gpt4)-12.6%
GSM8K: 69.67 vs 96.4 (so35)-27.7%
LLME Score: 0.21828
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)
Llama3 8B Sa V0.1 Parameters and Internals
| LLM Name | Llama3 8b Sa V0.1 |
| Repository 🤗 | https://huggingface.co/langgptai/llama3-8b_sa_v0.1 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0 GB |
| Updated | 2024-11-17 |
| Maintainer | langgptai |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Adapter |
| License | other |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|eot_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|q_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 8 |
Best Alternatives to Llama3 8B Sa V0.1
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ... 3 8B Instruct Bvr Finetune V3 | 8K / 16.1 GB | 5 | 0 |
| Vortex2 | 0K / 4.4 GB | 8 | 0 |
| FineLlama3.1 8B Instruct Lora | 0K / 0.2 GB | 0 | 1 |
| Llama3 8B Instruct Code | 0K / 0.2 GB | 9 | 1 |
| Llama 3 8B Claudstruct V3 | 0K / 0.1 GB | 9 | 0 |
| Llama 3 8B Instruct 80K QLoRA | 0K / 2.2 GB | 0 | 24 |
| Llama 3 8B Claudstruct V1 | 0K / 0.1 GB | 6 | 0 |
| ...Llama 3 8B Instruct ORPO QLoRA | 0K / 0.7 GB | 5 | 0 |
| Llama3 Tw 8B Btc Qlora | 0K / 0.1 GB | 10 | 3 |
| Results | 0K / 4.4 GB | 23 | 0 |
Note: green Score (e.g. "73.2") means that the model is better than langgptai/llama3-8b_sa_v0.1 .
Rank the Llama3 8B Sa V0.1 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? 38149 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110