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 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)
Llama 3 8B Finetuned Parameters and Internals
| Model Type |
| |||
| Training Details |
|
| LLM Name | Llama 3 8B Finetuned |
| Repository 🤗 | https://huggingface.co/fay-ong/llama-3-8b-finetuned |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.1 GB |
| Updated | 2024-11-21 |
| 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 |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Llama3 Aesir Preview LoRA 128 | 0K / 1.3 GB | 52 | 0 |
| ...ma3 Instruct Chat FCAIBylaw V1 | 0K / 0.2 GB | 9 | 0 |
| ...a 3 8B Arabic Customer Service | 0K / 0 GB | 5 | 0 |
| ... 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 |
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? 38149 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110