4-bit 4bit Adapter Base model:adapter:unsloth/lla... Base model:unsloth/llama-3-8b-... Bitsandbytes Finetuned Generated from trainer Instruct Llama Llama-factory Lora Peft Quantized Region:us Safetensors Tensorboard Unsloth
Llama 3 8B Finetuned Parameters and Internals
| LLM Name | Llama 3 8B Finetuned |
| Repository | Open on 🤗 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.1 GB |
| Updated | 2024-07-26 |
| Maintainer | fay-ong |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Adapter |
| License | apache-2.0 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|reserved_special_token_250|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | v_proj|o_proj|gate_proj|q_proj|k_proj|up_proj|down_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 8 |
Best Alternatives to Llama 3 8B Finetuned
Best Alternatives |
HF Rank |
Context/RAM |
Downloads |
Likes |
|---|---|---|---|---|
| ...ma3 Instruct Chat FCAIBylaw V1 | 0.3 | 0K / 0.2 GB | 131 | 0 |
| ...a 3 8B Arabic Customer Service | 0.2 | 0K / 0 GB | 5 | 0 |
| ... 3 8B Instruct Bvr Finetune V3 | 0.2 | 8K / 16.1 GB | 14 | 0 |
| Llama3 Rm 96k Summ | 0.3 | 0K / 0 GB | 87 | 0 |
| ...ta Llama 3 8B Instruct Chatbot | 0.3 | 0K / 2.5 GB | 71 | 0 |
| Llama3 Tw 8B Btc Qlora | 0.3 | 0K / 0.1 GB | 22 | 3 |
| Vortex2 | 0.3 | 0K / 4.4 GB | 8 | 0 |
| ...a 3 8B Instruct 2 Spider 3 DPO | 0.3 | 0K / 0.2 GB | 62 | 0 |
| Llama 3 8B Instruct 80K QLoRA | 0.3 | 0K / 2.2 GB | 0 | 20 |
| Llama3 8B Instruct Code | 0.3 | 0K / 0.2 GB | 6 | 1 |
Note: green Score (e.g. "73.2") means that the model is better than fay-ong/llama-3-8b-finetuned .
Rank the Llama 3 8B Finetuned 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