Upload README.md

README.md

@@ -10,6 +10,18 @@ model_creator: AIDC-ai-business
 model_name: Marcoroni 13B
 model_type: llama
 pipeline_tag: text-generation
+prompt_template: 'Below is an instruction that describes a task. Write a response
+  that appropriately completes the request.
+
+
+  ### Instruction:
+
+  {prompt}
+
+
+  ### Response:
+
+  '
 quantized_by: TheBloke
 ---
 
@@ -61,17 +73,23 @@ Here is an incomplate list of clients and libraries that are known to support GG
 <!-- repositories-available start -->
 ## Repositories available
 
+* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/Marcoroni-13B-AWQ)
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Marcoroni-13B-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Marcoroni-13B-GGUF)
 * [AIDC-ai-business's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/AIDC-ai-business/Marcoroni-13B)
 <!-- repositories-available end -->
 
 <!-- prompt-template start -->
-## Prompt template: Unknown
+## Prompt template: Alpaca
 
 ```
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+
+### Instruction:
 {prompt}
 
+### Response:
+
 ```
 
 <!-- prompt-template end -->
@@ -193,7 +211,7 @@ Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running
 Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 
 ```shell
-./main -ngl 32 -m marcoroni-13b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}"
+./main -ngl 32 -m marcoroni-13b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{prompt}\n\n### Response:"
 ```
 
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
@@ -306,15 +324,14 @@ Fine-tuned from Llama2-13B，we use Orca-style data and other open source data f
 ### Response:
 ```
 
-
 # Evulation Results ([Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard))
 
 | Metric                | Value |
 |-----------------------|-------|
-| Avg.                  |   65.23   |
-| ARC (25-shot)         |   63.31   |
-| HellaSwag (10-shot)   |   83.04   |
-| MMLU (5-shot)         |   58.78   |
-| TruthfulQA (0-shot)   |   55.79   |
+| Avg.                  |   65.76   |
+| ARC (25-shot)         |   62.46   |
+| HellaSwag (10-shot)   |   83.27   |
+| MMLU (5-shot)         |   59.63   |
+| TruthfulQA (0-shot)   |   57.7   |
 
 <!-- original-model-card end -->