Hugging Face's logo

digitalpipelines
/
llama2_7b_chat_uncensored

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
digitalpipelines commited on
Commit
4035a0c
·
1 Parent(s): f78c64d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -8,7 +8,8 @@ datasets:
8
  Fine-tuned [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b) with an uncensored/unfiltered Wizard-Vicuna conversation dataset [digitalpipelines/wizard_vicuna_70k_uncensored](https://huggingface.co/datasets/digitalpipelines/wizard_vicuna_70k_uncensored).
9
  Used QLoRA for fine-tuning using the process outlined in https://georgesung.github.io/ai/qlora-ift/
10
 
11
- A quantized GPTQ model can be found at [digitalpipelines/llama2_7b_chat_uncensored-GPTQ](https://huggingface.co/digitalpipelines/llama2_7b_chat_uncensored-GPTQ)
 
12
 
13
  # Prompt style
14
  The model was trained with the following prompt style:
 
8
  Fine-tuned [OpenLLaMA-7B](https://huggingface.co/openlm-research/open_llama_7b) with an uncensored/unfiltered Wizard-Vicuna conversation dataset [digitalpipelines/wizard_vicuna_70k_uncensored](https://huggingface.co/datasets/digitalpipelines/wizard_vicuna_70k_uncensored).
9
  Used QLoRA for fine-tuning using the process outlined in https://georgesung.github.io/ai/qlora-ift/
10
 
11
+ - GPTQ quantized model can be found at [digitalpipelines/llama2_7b_chat_uncensored-GPTQ](https://huggingface.co/digitalpipelines/llama2_7b_chat_uncensored-GPTQ)
12
+ - GGML 2, 3, 4, 5, 6 and 8-bit quanitized models for CPU+GPU inference of [digitalpipelines/llama2_7b_chat_uncensored-GGML](https://huggingface.co/digitalpipelines/llama2_7b_chat_uncensored-GGML)
13
 
14
  # Prompt style
15
  The model was trained with the following prompt style: