Arxiv:1910.09700 4-bit 4bit Adapter Base model:adapter:ryanjt/quan... Base model:ryanjt/quantized-gr... Bitsandbytes Finetuned Instruct Llama Lora Peft Quantized Region:us Safetensors
Model Card on HF 🤗: https://huggingface.co/RyanJT/trained-quant-4bit
Trained Quant 4bit 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)
Trained Quant 4bit Parameters and Internals
| LLM Name | Trained Quant 4bit |
| Repository 🤗 | https://huggingface.co/RyanJT/trained-quant-4bit |
| Base Model(s) | |
| Model Size | 3b |
| Required VRAM | 0 GB |
| Updated | 2024-08-15 |
| Maintainer | RyanJT |
| Instruction-Based | Yes |
| Model Files | |
| Quantization Type | 4bit |
| Model Architecture | Adapter |
| Model Max Length | 9223372036854775807 |
| Is Biased | none |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 49152 |
| PEFT Type | LORA |
| LoRA Model | Yes |
| PEFT Target Modules | q_proj|v_proj |
| LoRA Alpha | 32 |
| LoRA Dropout | 0.1 |
| R Param | 8 |
Best Alternatives to Trained Quant 4bit
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Xenith 3B | 0K / 7.6 GB | 0 | 2 |
Note: green Score (e.g. "73.2") means that the model is better than RyanJT/trained-quant-4bit .
Rank the Trained Quant 4bit 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? 40066 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217