Update README.md

README.md

@@ -1,6 +1,48 @@
 ---
 inference: false
-license: other
+pipeline_tag: text-generation
+widget:
+- text: 'def print_hello_world():'
+  example_title: Hello world
+  group: Python
+- text: 'Gradient descent is'
+  example_title: Machine Learning
+  group: English
+- license: bigcode-openrail-m
+datasets:
+- bigcode/the-stack-dedup
+- tiiuae/falcon-refinedweb
+- ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered
+- QingyiSi/Alpaca-CoT
+- teknium/GPTeacher-General-Instruct
+- metaeval/ScienceQA_text_only
+- hellaswag
+- openai/summarize_from_feedback
+- riddle_sense
+- gsm8k
+- camel-ai/math
+- camel-ai/biology
+- camel-ai/physics
+- camel-ai/chemistry
+- winglian/evals
+metrics:
+- code_eval
+- mmlu
+- arc
+- hellaswag
+- truthfulqa
+library_name: transformers
+tags:
+- code
+extra_gated_prompt: >-
+  ## Model License Agreement
+
+  Please read the BigCode [OpenRAIL-M
+  license](https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement)
+  agreement before accepting it.
+    
+extra_gated_fields:
+  I accept the above license agreement, and will use the Model complying with the set of use restrictions and sharing requirements: checkbox
 ---
 
 <!-- header start -->
@@ -29,6 +71,18 @@ It is the result of quantising to 4bit using [GPTQ-for-LLaMa](https://github.com
 * [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/minotaur-15B-GGML)
 * [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openaccess-ai-collective/minotaur-15b)
 
+## Note about context length
+
+It is currently untested as to whether the 8K context is compatible with available clients such as text-generation-webui.
+
+If you have feedback on this, please let me know.
+
+## Prompt template
+```
+USER: <prompt>
+ASSISTANT:
+```
+
 ## How to easily download and use this model in text-generation-webui
 
 Please make sure you're using the latest version of text-generation-webui
@@ -74,8 +128,8 @@ model = AutoGPTQForCausalLM.from_quantized(model_name_or_path,
 
 # Note: check the prompt template is correct for this model.
 prompt = "Tell me about AI"
-prompt_template=f'''### Human: {prompt}
-### Assistant:'''
+prompt_template=f'''USER: {prompt}
+ASSISTANT:'''
 
 print("\n\n*** Generate:")
 
@@ -114,6 +168,7 @@ It was created with group_size 128 to increase inference accuracy, but without -
   * 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.
   * Works with text-generation-webui, including one-click-installers.
+  * Does not work with ExLlama, as it is not a Llama model.
   * Parameters: Groupsize = 128. Act Order / desc_act = False.
 
 <!-- footer start -->