Initial GPTQ model commit

README.md

@@ -1,8 +1,6 @@
 ---
 inference: false
 license: other
-datasets:
-- jondurbin/airoboros-gpt4-1.2
 ---
 
 <!-- header start -->
@@ -29,15 +27,7 @@ It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com
 
 * [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-13B-gpt4-1.2-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/airoboros-13B-gpt4-1.2-GGML)
-* [Unquantised fp32 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.2)
-
-## Prompt template
-
-```
-A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input.
-USER: prompt
-ASSISTANT:
-```
+* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-13b-gpt4-1.2)
 
 ## How to easily download and use this model in text-generation-webui
 
@@ -118,6 +108,8 @@ print(pipe(prompt_template)[0]['generated_text'])
 
 This will work with AutoGPTQ and CUDA versions of GPTQ-for-LLaMa. There are reports of issues with Triton mode of recent GPTQ-for-LLaMa. If you have issues, please use AutoGPTQ instead.
 
+
+
 * `airoboros-13b-gpt4-1.2-GPTQ-4bit-128g.act.order.safetensors`
   * Works with AutoGPTQ in CUDA or Triton modes.
   * Works with GPTQ-for-LLaMa in CUDA mode.  May have issues with GPTQ-for-LLaMa Triton mode.