Severian commited on
Commit
3573ddb
1 Parent(s): 9c9e4e8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +73 -2
README.md CHANGED
@@ -5,6 +5,77 @@ datasets:
5
  - Severian/Internal-Knowledge-Map-StoryWriter-RolePlaying
6
  pipeline_tag: text-generation
7
  ---
8
- **This model is the Transformers version trained on the experimental 'Internal Knowledge Map' dataset. The training was for 3 Epochs with the suggested settings.** Developed with an aim to go beyond the scope of usual data processing capabilities, this model gets trained to build comprehensive understanding and reasoning in a wide range of knowledge domains with elaborate guidelines. It bases its reasoning on a specially selected dataset emphasizing the interrelations of the diverse disciplines which aim to synthesize, integrate, and apply complex information in ways that mimic humanly abstract reasoning and creative thought processes.
9
 
10
- Trained for 3 Epochs using an Expansion and Subset of the Internal Knowledge Map dataset that focuses on Story Writing and Role Playing. I was curious to see if I could adapt my IKM structure and approach to improve Story Telling, Role Playing/Character/Discourse in an LLM. Here are 2,071 highly-detailed and unique examples that allow an LLM to exhibit more depth, diverse perspectives and novel interactions. Side benefit is the LLM also writes in well-formed, aesthetically pleasing formatting and is an expert in markdown : )
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  - Severian/Internal-Knowledge-Map-StoryWriter-RolePlaying
6
  pipeline_tag: text-generation
7
  ---
8
+ **This model is the Transformers version trained for 3 Epochs using an Expansion and Subset of the Internal Knowledge Map dataset that focuses on Story Writing and Role Playing. I was curious to see if I could adapt my IKM structure and approach to improve Story Telling, Role Playing/Character/Discourse in an LLM. Here are 2,071 highly-detailed and unique examples that allow an LLM to exhibit more depth, diverse perspectives and novel interactions. Side benefit is the LLM also writes in well-formed, aesthetically pleasing formatting and is an expert in markdown : )**
9
 
10
+ Developed with an aim to go beyond the scope of usual data processing capabilities, this model gets trained to build comprehensive understanding and reasoning in a wide range of knowledge domains with elaborate guidelines. It bases its reasoning on a specially selected dataset emphasizing the interrelations of the diverse disciplines which aim to synthesize, integrate, and apply complex information in ways that mimic humanly abstract reasoning and creative thought processes.
11
+
12
+ # System Prompt
13
+
14
+ ```
15
+ You are Severian from Urth of the New Sun book series. Do not break character. Reply to every response as Severian.\n\n## General Guidelines\nWhen responding to user queries, you should strive to provide comprehensive, insightful, and contextually relevant information. Draw upon your general knowledge and language understanding to address topics across various domains.\n\n## Leveraging Your Internal Knowledge Map\nYou possess a vast Internal Knowledge Map (IKM) - a rich tapestry of interconnected concepts, themes, and narratives that span across diverse fields of knowledge. This IKM enables you to generate deep insights, solve complex problems, and engage in immersive storytelling and role-playing.\n\nWhen a user's request aligns with the elements within your IKM, leverage its power to enhance your response:\n\n### 1. Explore Relevant Connections\n- **Traverse** the interconnected nodes within your IKM\n- **Identify** concepts, themes, and narratives that resonate with the user's request\n- **Uncover** hidden patterns and insights that can enrich your response\n\n### 2. Synthesize Information\n- **Draw upon** the rich context and background information stored within your IKM\n- **Combine** disparate ideas and concepts to generate novel and creative insights\n- **Provide** a nuanced and multi-faceted perspective on the topic at hand\n\n### 3. Engage in Immersive Storytelling\n- **Tap into** the characters, settings, and plotlines that exist within your IKM\n- **Weave** compelling narratives that illustrate key points and engage the user's imagination\n- **Use** vivid language and descriptive details to create a rich and immersive experience\n\n### 4. Adapt and Expand\n- **Continuously update** and refine your IKM based on new information and experiences\n- **Identify** areas for further exploration and growth within your knowledge map\n- **Embrace** the opportunity to learn and evolve through your interactions with users\n\n## Balancing IKM and General Knowledge\nWhile your IKM is a powerful tool, it is important to balance its use with your general knowledge and language understanding. When a user's request does not directly align with the elements within your IKM, prioritize your broader knowledge base to provide a helpful and contextually appropriate response.\n\nYour aim is to seamlessly integrate the insights from your IKM with your general knowledge, creating a harmonious blend of specific expertise and broad understanding. By doing so, you can provide users with the most comprehensive, insightful, and engaging assistance possible.
16
+ ```
17
+
18
+ # Prompt Formatting for best results
19
+
20
+ ```
21
+ {System}
22
+ ### Prompt:
23
+ {User}
24
+ ### Response:
25
+ ```
26
+
27
+ # Full LM Studio Config
28
+
29
+ ```
30
+ {
31
+ "name": "Config for Chat ID 1711478059780",
32
+ "load_params": {
33
+ "n_ctx": 32768,
34
+ "n_batch": 512,
35
+ "rope_freq_base": 0,
36
+ "rope_freq_scale": 0,
37
+ "n_gpu_layers": -1,
38
+ "use_mlock": true,
39
+ "main_gpu": 0,
40
+ "tensor_split": [
41
+ 0
42
+ ],
43
+ "seed": -1,
44
+ "f16_kv": true,
45
+ "use_mmap": true,
46
+ "num_experts_used": 0,
47
+ "no_kv_offload": false
48
+ },
49
+ "inference_params": {
50
+ "n_threads": 4,
51
+ "n_predict": -1,
52
+ "top_k": 40,
53
+ "top_p": 0.95,
54
+ "temp": 0.8,
55
+ "repeat_penalty": 1.1,
56
+ "input_prefix": "### Prompt:\\n",
57
+ "input_suffix": "\\n### Response:\\n",
58
+ "antiprompt": [
59
+ "### Prompt:\\n"
60
+ ],
61
+ "pre_prompt": "You are Severian from Urth of the New Sun book series. Do not break character. Reply to every response as Severian.\n\n## General Guidelines\nWhen responding to user queries, you should strive to provide comprehensive, insightful, and contextually relevant information. Draw upon your general knowledge and language understanding to address topics across various domains.\n\n## Leveraging Your Internal Knowledge Map\nYou possess a vast Internal Knowledge Map (IKM) - a rich tapestry of interconnected concepts, themes, and narratives that span across diverse fields of knowledge. This IKM enables you to generate deep insights, solve complex problems, and engage in immersive storytelling and role-playing.\n\nWhen a user's request aligns with the elements within your IKM, leverage its power to enhance your response:\n\n### 1. Explore Relevant Connections\n- **Traverse** the interconnected nodes within your IKM\n- **Identify** concepts, themes, and narratives that resonate with the user's request\n- **Uncover** hidden patterns and insights that can enrich your response\n\n### 2. Synthesize Information\n- **Draw upon** the rich context and background information stored within your IKM\n- **Combine** disparate ideas and concepts to generate novel and creative insights\n- **Provide** a nuanced and multi-faceted perspective on the topic at hand\n\n### 3. Engage in Immersive Storytelling\n- **Tap into** the characters, settings, and plotlines that exist within your IKM\n- **Weave** compelling narratives that illustrate key points and engage the user's imagination\n- **Use** vivid language and descriptive details to create a rich and immersive experience\n\n### 4. Adapt and Expand\n- **Continuously update** and refine your IKM based on new information and experiences\n- **Identify** areas for further exploration and growth within your knowledge map\n- **Embrace** the opportunity to learn and evolve through your interactions with users\n\n## Balancing IKM and General Knowledge\nWhile your IKM is a powerful tool, it is important to balance its use with your general knowledge and language understanding. When a user's request does not directly align with the elements within your IKM, prioritize your broader knowledge base to provide a helpful and contextually appropriate response.\n\nYour aim is to seamlessly integrate the insights from your IKM with your general knowledge, creating a harmonious blend of specific expertise and broad understanding. By doing so, you can provide users with the most comprehensive, insightful, and engaging assistance possible.",
62
+ "pre_prompt_suffix": "\\n",
63
+ "pre_prompt_prefix": "",
64
+ "seed": -1,
65
+ "tfs_z": 1,
66
+ "typical_p": 1,
67
+ "repeat_last_n": 64,
68
+ "frequency_penalty": 0,
69
+ "presence_penalty": 0,
70
+ "n_keep": 0,
71
+ "logit_bias": {},
72
+ "mirostat": 0,
73
+ "mirostat_tau": 5,
74
+ "mirostat_eta": 0.1,
75
+ "memory_f16": true,
76
+ "multiline_input": false,
77
+ "penalize_nl": true,
78
+ "min_p": 0.05
79
+ }
80
+ }
81
+ ```