4bit Am Ar Dataset:vutuka/aya african alp... En Endpoints compatible Fr Gguf Ha Ig Llama Lora Quantized Region:us Safetensors Sn So Sw Trl Unsloth Wo Xh Yo Zu
Llama 3.1 8B African Aya 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 3.1 8B African Aya Parameters and Internals
| LLM Name | Llama 3.1 8B African Aya |
| Repository 🤗 | https://huggingface.co/vutuka/Llama-3.1-8B-african-aya |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 0.2 GB |
| Updated | 2024-09-07 |
| Maintainer | vutuka |
| Model Files | |
| Supported Languages | en yo zu xh wo fr ig ha am ar so sw sn |
| GGUF Quantization | Yes |
| Quantization Type | gguf|4bit |
| Model Architecture | AutoModel |
| License | apache-2.0 |
| Model Max Length | 131072 |
| Is Biased | none |
| Tokenizer Class | PreTrainedTokenizerFast |
| Padding Token | <|finetune_right_pad_id|> |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | down_proj|v_proj|gate_proj|k_proj|q_proj|o_proj|up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 16 |
Best Alternatives to Llama 3.1 8B African Aya
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Meta Llama 3 8B Instruct GGUF | 0K / 3.2 GB | 20149 | 33 |
| Granite 8B Code Instruct GGUF | 0K / 3.1 GB | 29788 | 3 |
| ...ist 8B EarlyPrototype 0.4 GGUF | 0K / GB | 6156 | 0 |
| GOAT Coder Llama3.1 8B | 0K / 16.1 GB | 304 | 1 |
| Meta Llama 3 8B Instruct GGUF | 0K / 2 GB | 1331 | 76 |
| ...ma 3 8B Instruct 32K V0.1 GGUF | 0K / 2 GB | 1441 | 56 |
| WizardHermes 2 Pro Llama 3 8B | 0K / 0 GB | 1766 | 1 |
| Smaugredq | 0K / 4.9 GB | 38 | 0 |
| New Ollama | 0K / 4.9 GB | 266 | 0 |
| Llama 3 8B Instruct V0.10 GGUF | 0K / 2 GB | 410 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than vutuka/Llama-3.1-8B-african-aya .
Rank the Llama 3.1 8B African Aya 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