4bit Alpaca Autotrain compatible En Endpoints compatible Gguf Llama Lora Model-index Quantized Region:us Rewiz Safetensors Sft Sharded Tensorflow Trl Unsloth
Model Card on HF 🤗: https://huggingface.co/theprint/ReWiz-Llama-3.1-8B-v2
ReWiz Llama 3.1 8B V2 Benchmarks
MMLU Pro: 25.67
GPQA: 7.05
MUSR: 9.34
BBH: 23.77
IFEval: 23.79 vs 88 (so35)-73%
MATH Lvl 5: 5.74
LLME Score: 0.23517
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)
ReWiz Llama 3.1 8B V2 Parameters and Internals
| LLM Name | ReWiz Llama 3.1 8B V2 |
| Repository 🤗 | https://huggingface.co/theprint/ReWiz-Llama-3.1-8B-v2 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-09-23 |
| Maintainer | theprint |
| Model Files | |
| Supported Languages | en |
| GGUF Quantization | Yes |
| Quantization Type | 4bit|gguf |
| Model Architecture | AutoModelForCausalLM |
| 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 | k_proj|q_proj|gate_proj|down_proj|v_proj|o_proj|up_proj |
| LoRA Alpha | 16 |
| LoRA Dropout | 0 |
| R Param | 8 |
Best Alternatives to ReWiz Llama 3.1 8B V2
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Fin Llama3.1 8B | 0K / 16.1 GB | 1478 | 0 |
| TalktoaiZERO | 0K / 16.1 GB | 70 | 5 |
| Llama 3 8B Chat Doctor | 0K / 16.1 GB | 15 | 0 |
| Llama 3 8B Chat Doctor | 0K / 16.1 GB | 7 | 0 |
| Genesist 8B EarlyPrototype 0.3 | 0K / 16.1 GB | 86 | 0 |
| Llama 3 8B Chat Me | 0K / 16.1 GB | 21 | 0 |
| Llama 3 8B Chat Doctor | 0K / 16.1 GB | 6 | 0 |
| Llama3 Credpol | 0K / 21.9 GB | 8 | 0 |
| Llm Nl To Cmd | 0K / 16.1 GB | 12 | 0 |
| Fine Tuning Bebidas | 0K / 16.1 GB | 5 | 0 |
Rank the ReWiz Llama 3.1 8B V2 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? 51545 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124