Upload README.md

README.md

@@ -12,11 +12,13 @@ license:
 model_creator: NousResearch
 model_name: Nous Capybara 34B
 model_type: yi
-prompt_template: 'USER: {prompt} ASSISTANT:'
+prompt_template: 'USER: {prompt} ASSISTANT:
+
+  '
 quantized_by: TheBloke
 tags:
 - sft
-- StableLM
+- Yi-34B-200K
 ---
 <!-- markdownlint-disable MD041 -->
 
@@ -79,7 +81,10 @@ Here is an incomplete list of clients and libraries that are known to support GG
 <!-- prompt-template start -->
 ## Prompt template: User-Assistant
 
-```USER: {prompt} ASSISTANT:```
+```
+USER: {prompt} ASSISTANT:
+
+```
 
 <!-- prompt-template end -->
 
@@ -196,7 +201,7 @@ Windows Command Line users: You can set the environment variable by running `set
 Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.
 
 ```shell
-./main -ngl 32 -m nous-capybara-34b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "USER: {prompt}\nASSISTANT:"
+./main -ngl 32 -m nous-capybara-34b.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "USER: {prompt} ASSISTANT:"
 ```
 
 Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
@@ -298,7 +303,7 @@ And thank you again to a16z for their generous grant.
 
 The Capybara series is the first Nous collection of models made by fine-tuning mostly on data created by Nous in-house.
 
-We leverage our novel data synthesis technique called Amplify-instruct (Paper coming soon), the seed distribution and synthesis method are comprised of a synergistic combination of top performing existing data synthesis techniques and distributions used for SOTA models such as Airoboros, Evol-Instruct(WizardLM), Orca, Vicuna, Know_Logic, Lamini, FLASK and others, all into one lean holistically formed methodology for the dataset and model. The seed instructions used for the start of synthesized conversations are largely based on highly datasets like Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from posts on the website LessWrong, as well as being supplemented with certain in-house multi-turn datasets like Dove(A successor to Puffin).
+We leverage our novel data synthesis technique called Amplify-instruct (Paper coming soon), the seed distribution and synthesis method are comprised of a synergistic combination of top performing existing data synthesis techniques and distributions used for SOTA models such as Airoboros, Evol-Instruct(WizardLM), Orca, Vicuna, Know_Logic, Lamini, FLASK and others, all into one lean holistically formed methodology for the dataset and model. The seed instructions used for the start of synthesized conversations are largely based on highly regarded datasets like Airoboros, Know logic, EverythingLM, GPTeacher and even entirely new seed instructions derived from posts on the website LessWrong, as well as being supplemented with certain in-house multi-turn datasets like Dove(A successor to Puffin).
 
 While performing great in it's current state, the current dataset used for fine-tuning is entirely contained within 20K training examples, this is 10 times smaller than many similar performing current models, this is signficant when it comes to scaling implications for our next generation of models once we scale our novel syntheiss methods to significantly more examples.
 
@@ -323,11 +328,13 @@ Datasets in Blue are in-house curations that previously existed prior to Capybar
 
 The reccomended model usage is:
 
-```
-USER:
 
-ASSISTANT:
-```
+Prefix: ``USER:``
+
+Suffix: ``ASSISTANT:``
+
+Stop token: ``</s>``
+
 
 ## Mutli-Modality!