|
--- |
|
base_model: acrastt/Marx-3B-V2 |
|
datasets: |
|
- totally-not-an-llm/EverythingLM-data-V2-sharegpt |
|
inference: false |
|
language: |
|
- en |
|
library_name: transformers |
|
license: apache-2.0 |
|
model_creator: acrastt |
|
model_name: Marx-3B-V2 |
|
pipeline_tag: text-generation |
|
quantized_by: afrideva |
|
tags: |
|
- gguf |
|
- ggml |
|
- quantized |
|
- q2_k |
|
- q3_k_m |
|
- q4_k_m |
|
- q5_k_m |
|
- q6_k |
|
- q8_0 |
|
--- |
|
# acrastt/Marx-3B-V2-GGUF |
|
|
|
Quantized GGUF model files for [Marx-3B-V2](https://huggingface.co/acrastt/Marx-3B-V2) from [acrastt](https://huggingface.co/acrastt) |
|
|
|
|
|
| Name | Quant method | Size | |
|
| ---- | ---- | ---- | |
|
| [marx-3b-v2.fp16.gguf](https://huggingface.co/afrideva/Marx-3B-V2-GGUF/resolve/main/marx-3b-v2.fp16.gguf) | fp16 | 6.85 GB | |
|
| [marx-3b-v2.q2_k.gguf](https://huggingface.co/afrideva/Marx-3B-V2-GGUF/resolve/main/marx-3b-v2.q2_k.gguf) | q2_k | 2.15 GB | |
|
| [marx-3b-v2.q3_k_m.gguf](https://huggingface.co/afrideva/Marx-3B-V2-GGUF/resolve/main/marx-3b-v2.q3_k_m.gguf) | q3_k_m | 2.27 GB | |
|
| [marx-3b-v2.q4_k_m.gguf](https://huggingface.co/afrideva/Marx-3B-V2-GGUF/resolve/main/marx-3b-v2.q4_k_m.gguf) | q4_k_m | 2.58 GB | |
|
| [marx-3b-v2.q5_k_m.gguf](https://huggingface.co/afrideva/Marx-3B-V2-GGUF/resolve/main/marx-3b-v2.q5_k_m.gguf) | q5_k_m | 2.76 GB | |
|
| [marx-3b-v2.q6_k.gguf](https://huggingface.co/afrideva/Marx-3B-V2-GGUF/resolve/main/marx-3b-v2.q6_k.gguf) | q6_k | 3.64 GB | |
|
| [marx-3b-v2.q8_0.gguf](https://huggingface.co/afrideva/Marx-3B-V2-GGUF/resolve/main/marx-3b-v2.q8_0.gguf) | q8_0 | 3.64 GB | |
|
|
|
|
|
|
|
## Original Model Card: |
|
<a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a> |
|
|
|
This is [OpenLLaMA 3B V2](https://huggingface.co/openlm-research/open_llama_3b_v2) finetuned on [EverythingLM Data V2(ShareGPT format)](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V2-sharegpt) for 2 epochs. |
|
|
|
Prompt template: |
|
``` |
|
### HUMAN: |
|
{prompt} |
|
|
|
### RESPONSE: |
|
<leave a newline for the model to answer> |
|
``` |
|
q4_1 GGML quant available [here](https://huggingface.co/NikolayKozloff/Marx-3B-V2/).</br> |
|
q4_1 GGUF quant available [here]( https://huggingface.co/NikolayKozloff/Marx-3B-V2-GGUF/). |
