Upload README.md

README.md

@@ -7,7 +7,7 @@ language:
 - en
 library_name: transformers
 license: apache-2.0
-model_creator: Jet Davis
+model_creator: Devin Gulliver
 model_name: OpenInstruct Mistral 7B
 model_type: mistral
 pipeline_tag: text-generation
@@ -45,13 +45,13 @@ quantized_by: TheBloke
 <!-- header end -->
 
 # OpenInstruct Mistral 7B - AWQ
-- Model creator: [Jet Davis](https://huggingface.co/monology)
+- Model creator: [Devin Gulliver](https://huggingface.co/monology)
 - Original model: [OpenInstruct Mistral 7B](https://huggingface.co/monology/openinstruct-mistral-7b)
 
 <!-- description start -->
 ## Description
 
-This repo contains AWQ model files for [Jet Davis's OpenInstruct Mistral 7B](https://huggingface.co/monology/openinstruct-mistral-7b).
+This repo contains AWQ model files for [Devin Gulliver's OpenInstruct Mistral 7B](https://huggingface.co/monology/openinstruct-mistral-7b).
 
 These files were quantised using hardware kindly provided by [Massed Compute](https://massedcompute.com/).
 
@@ -75,7 +75,7 @@ It is supported by:
 * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/openinstruct-mistral-7B-AWQ)
 * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/openinstruct-mistral-7B-GPTQ)
 * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/openinstruct-mistral-7B-GGUF)
-* [Jet Davis's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/monology/openinstruct-mistral-7b)
+* [Devin Gulliver's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/monology/openinstruct-mistral-7b)
 <!-- repositories-available end -->
 
 <!-- prompt-template start -->
@@ -103,7 +103,7 @@ Models are released as sharded safetensors files.
 
 | Branch | Bits | GS | AWQ Dataset | Seq Len | Size |
 | ------ | ---- | -- | ----------- | ------- | ---- |
-| [main](https://huggingface.co/TheBloke/openinstruct-mistral-7B-AWQ/tree/main) | 4 | 128 | [open-instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.15 GB
+| [main](https://huggingface.co/TheBloke/openinstruct-mistral-7B-AWQ/tree/main) | 4 | 128 | [VMware Open Instruct](https://huggingface.co/datasets/VMware/open-instruct/viewer/) | 4096 | 4.15 GB
 
 <!-- README_AWQ.md-provided-files end -->
 
@@ -372,7 +372,7 @@ And thank you again to a16z for their generous grant.
 
 <!-- footer end -->
 
-# Original model card: Jet Davis's OpenInstruct Mistral 7B
+# Original model card: Devin Gulliver's OpenInstruct Mistral 7B
 
 
 # OpenInstruct Mistral-7B
@@ -383,7 +383,7 @@ Quantized to FP16 and released under the [Apache-2.0](https://choosealicense.com
 Compute generously provided by [Higgsfield AI](https://higgsfield.ai/model/655559e6b5777dab620095e0).  
 
 
-Prompt format: Alpaca
+## Prompt format: Alpaca
 ```
 Below is an instruction that describes a task. Write a response that appropriately completes the request.
 
@@ -393,4 +393,10 @@ Below is an instruction that describes a task. Write a response that appropriate
 ### Response:
 ```
 
+## Recommended preset:
+- temperature: 0.2
+- top_k: 50
+- top_p 0.95
+- repetition_penalty: 1.1
+
 \*as of 21 Nov 2023. "commercially-usable" includes both an open-source base model and a *non-synthetic* open-source finetune dataset. updated leaderboard results available [here](https://huggingfaceh4-open-llm-leaderboard.hf.space).