---
base_model: marianna13/llava-phi-2-3b
pipeline_tag: text-generation
inference: false
quantized_by: Kevin Cao
language:
- en
license: mit
library_name: transformers
datasets:
- liuhaotian/LLaVA-Instruct-150K
- liuhaotian/LLaVA-Pretrain
---

# GGUF Quantized LLaVa Phi-2 3B

Original model from [marianna13/llava-phi-2-3b](https://huggingface.co/marianna13/llava-phi-2-3b).

## Provided Files

| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [ggml-model-Q2_K.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q2_K.gguf) | Q2_K | 2 | 1.17 GB| 3.67 GB | smallest, significant quality loss - not recommended for most purposes |
| [ggml-model-Q3_K_S.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q3_K_S.gguf) | Q3_K_S | 3 | 1.25 GB| 3.75 GB | very small, high quality loss |
| [ggml-model-Q3_K_M.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q3_K_M.gguf) | Q3_K_M | 3 | 1.48 GB| 3.98 GB | very small, high quality loss |
| [ggml-model-Q4_0.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q4_0.gguf) | Q4_0 | 4 | 1.60 GB| 4.10 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [ggml-model-Q3_K_L.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q3_K_L.gguf) | Q3_K_L | 3 | 1.60 GB| 4.10 GB | small, substantial quality loss |
| [ggml-model-Q4_K_S.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q4_K_S.gguf) | Q4_K_S | 4 | 1.62 GB| 4.12 GB | small, greater quality loss |
| [ggml-model-Q4_K_M.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q4_K_M.gguf) | Q4_K_M | 4 | 1.79 GB| 4.29 GB | medium, balanced quality - recommended |
| [ggml-model-Q5_0.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q5_0.gguf) | Q5_0 | 5 | 1.93 GB| 4.43 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [ggml-model-Q5_K_S.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q5_K_S.gguf) | Q5_K_S | 5 | 1.93 GB| 4.43 GB | large, low quality loss - recommended |
| [ggml-model-Q5_K_M.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q5_K_M.gguf) | Q5_K_M | 5 | 2.07 GB| 4.57 GB | large, very low quality loss - recommended |
| [ggml-model-Q6_K.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q6_K.gguf) | Q6_K | 6 | 2.29 GB| 4.79 GB | very large, extremely low quality loss |
| [ggml-model-Q8_0.gguf](https://huggingface.co/kejcao/llava-phi-2-GGUF/blob/main/ggml-model-Q8_0.gguf) | Q8_0 | 8 | 2.96 GB| 5.46 GB | very large, extremely low quality loss - not recommended |

# ORIGINAL MODEL CARD

# Model Card for LLaVa-Phi-2-3B

<!-- Provide a quick summary of what the model is/does. -->

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->


- **Developed by:** [LAION](https://laion.ai/), [SkunkworksAI](https://huggingface.co/SkunkworksAI) & [Ontocord](https://www.ontocord.ai/)
- **Model type:** LLaVA is an open-source chatbot trained by fine-tuning Phi-2 on GPT-generated multimodal instruction-following data.
It is an auto-regressive language model, based on the transformer architecture
- **Finetuned from model:** [Phi-2](https://huggingface.co/microsoft/phi-2)
- **License:** MIT
- **Demo:** [llava-phi-2-3b-demo](https://huggingface.co/spaces/marianna13/llava-phi-2-3b-demo) 

### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** [BakLLaVa](https://github.com/SkunkworksAI/BakLLaVA)

## Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

### Benchmarks

| Model | Parameters |SQA | GQA | TextVQA | POPE |
| --- | --- | --- | --- | --- | --- |
| [LLaVA-1.5](https://huggingface.co/liuhaotian/llava-v1.5-7b) |  7.3B | 68.0| **62.0** | **58.3** | 85.3 |
| [MC-LLaVA-3B](https://huggingface.co/visheratin/MC-LLaVA-3b) | 3B | - | 49.6 | 38.59 | - |
| [LLaVA-Phi](https://arxiv.org/pdf/2401.02330.pdf) | 3B | 68.4 | - | 48.6 | 85.0 |
| [moondream1](https://huggingface.co/vikhyatk/moondream1) | 1.6B | - | 56.3 | 39.8 | - |
| **llava-phi-2-3b** | 3B | **69.0** | 51.2 | 47.0 | **86.0** |

### Image Captioning (MS COCO)

| Model                                                    | BLEU_1 | BLEU_2 | BLEU_3 | BLEU_4 | METEOR | ROUGE_L | CIDEr | SPICE |
| -------------------------------------------------------- | ------ | ------ | ------ | ------ | ------ | ------- | ----- | ----- |
| llava-1.5-7b                                             | 75.8   | 59.8   | 45     | 33.3   | 29.4   | 57.7    | 108.8 | 23.5  |
| **llava-phi-2-3b** | 67.7   | 50.5   | 35.7   | 24.2   | 27.0   | 52.4   | 85.0  | 20.7  |