65 lines
2.8 KiB
Markdown
65 lines
2.8 KiB
Markdown
---
|
|
base_model: haramberesearch/llama2_xs_460M_uncensored
|
|
datasets:
|
|
- unalignment/toxic-dpo-v0.1
|
|
inference: false
|
|
model_creator: haramberesearch
|
|
model_name: llama2_xs_460M_uncensored
|
|
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
|
|
---
|
|
# haramberesearch/llama2_xs_460M_uncensored-GGUF
|
|
|
|
Quantized GGUF model files for [llama2_xs_460M_uncensored](https://huggingface.co/haramberesearch/llama2_xs_460M_uncensored) from [haramberesearch](https://huggingface.co/haramberesearch)
|
|
|
|
|
|
| Name | Quant method | Size |
|
|
| ---- | ---- | ---- |
|
|
| [llama2_xs_460m_uncensored.fp16.gguf](https://huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF/resolve/main/llama2_xs_460m_uncensored.fp16.gguf) | fp16 | 925.45 MB |
|
|
| [llama2_xs_460m_uncensored.q2_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF/resolve/main/llama2_xs_460m_uncensored.q2_k.gguf) | q2_k | 212.56 MB |
|
|
| [llama2_xs_460m_uncensored.q3_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF/resolve/main/llama2_xs_460m_uncensored.q3_k_m.gguf) | q3_k_m | 238.87 MB |
|
|
| [llama2_xs_460m_uncensored.q4_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF/resolve/main/llama2_xs_460m_uncensored.q4_k_m.gguf) | q4_k_m | 288.52 MB |
|
|
| [llama2_xs_460m_uncensored.q5_k_m.gguf](https://huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF/resolve/main/llama2_xs_460m_uncensored.q5_k_m.gguf) | q5_k_m | 333.29 MB |
|
|
| [llama2_xs_460m_uncensored.q6_k.gguf](https://huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF/resolve/main/llama2_xs_460m_uncensored.q6_k.gguf) | q6_k | 380.87 MB |
|
|
| [llama2_xs_460m_uncensored.q8_0.gguf](https://huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF/resolve/main/llama2_xs_460m_uncensored.q8_0.gguf) | q8_0 | 492.67 MB |
|
|
|
|
|
|
|
|
## Original Model Card:
|
|
# llama2_xs_460M_uncensored
|
|
## Model Details
|
|
|
|
[llama2_xs_460M_experimental](https://huggingface.co/ahxt/llama2_xs_460M_experimental) DPO finedtuned to remove alignment (3 epochs QLoRa).
|
|
|
|
### Model Description
|
|
|
|
<!-- Provide a longer summary of what this model is. -->
|
|
|
|
- **Developed by:** Harambe Research
|
|
- **Model type:** llama2
|
|
- **Finetuned from model:** [llama2_xs_460M_experimental](https://huggingface.co/ahxt/llama2_xs_460M_experimental)
|
|
|
|
### Out-of-Scope Use
|
|
|
|
Don't use this to do bad things. Bad things are bad.
|
|
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
|
|
|
### Recommendations
|
|
|
|
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
|
|
|
Users (both direct and downstream) should be aware of the risks, biases and limitations of the model.
|
|
|
|
## How to Get Started with the Model
|
|
|
|
https://github.com/oobabooga/text-generation-webui |