starsnatched
commited on
Commit
•
9ad14e5
1
Parent(s):
6922082
Upload README.md
Browse files
README.md
CHANGED
@@ -1,201 +1,69 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
4 |
---
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
-
|
23 |
-
|
24 |
-
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
|
45 |
-
|
46 |
-
|
47 |
-
|
48 |
-
|
49 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
65 |
-
|
66 |
-
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
-
|
68 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
-
|
70 |
-
## How to Get Started with the Model
|
71 |
-
|
72 |
-
Use the code below to get started with the model.
|
73 |
-
|
74 |
-
[More Information Needed]
|
75 |
-
|
76 |
-
## Training Details
|
77 |
-
|
78 |
-
### Training Data
|
79 |
-
|
80 |
-
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
-
|
82 |
-
[More Information Needed]
|
83 |
-
|
84 |
-
### Training Procedure
|
85 |
-
|
86 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
-
|
88 |
-
#### Preprocessing [optional]
|
89 |
-
|
90 |
-
[More Information Needed]
|
91 |
-
|
92 |
-
|
93 |
-
#### Training Hyperparameters
|
94 |
-
|
95 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
-
|
97 |
-
#### Speeds, Sizes, Times [optional]
|
98 |
-
|
99 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
-
|
101 |
-
[More Information Needed]
|
102 |
-
|
103 |
-
## Evaluation
|
104 |
-
|
105 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
-
|
107 |
-
### Testing Data, Factors & Metrics
|
108 |
-
|
109 |
-
#### Testing Data
|
110 |
-
|
111 |
-
<!-- This should link to a Dataset Card if possible. -->
|
112 |
-
|
113 |
-
[More Information Needed]
|
114 |
-
|
115 |
-
#### Factors
|
116 |
-
|
117 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
-
|
119 |
-
[More Information Needed]
|
120 |
-
|
121 |
-
#### Metrics
|
122 |
-
|
123 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
-
|
125 |
-
[More Information Needed]
|
126 |
-
|
127 |
-
### Results
|
128 |
-
|
129 |
-
[More Information Needed]
|
130 |
-
|
131 |
-
#### Summary
|
132 |
-
|
133 |
-
|
134 |
-
|
135 |
-
## Model Examination [optional]
|
136 |
-
|
137 |
-
<!-- Relevant interpretability work for the model goes here -->
|
138 |
-
|
139 |
-
[More Information Needed]
|
140 |
-
|
141 |
-
## Environmental Impact
|
142 |
-
|
143 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
-
|
145 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
-
|
147 |
-
- **Hardware Type:** [More Information Needed]
|
148 |
-
- **Hours used:** [More Information Needed]
|
149 |
-
- **Cloud Provider:** [More Information Needed]
|
150 |
-
- **Compute Region:** [More Information Needed]
|
151 |
-
- **Carbon Emitted:** [More Information Needed]
|
152 |
-
|
153 |
-
## Technical Specifications [optional]
|
154 |
-
|
155 |
-
### Model Architecture and Objective
|
156 |
-
|
157 |
-
[More Information Needed]
|
158 |
-
|
159 |
-
### Compute Infrastructure
|
160 |
-
|
161 |
-
[More Information Needed]
|
162 |
-
|
163 |
-
#### Hardware
|
164 |
-
|
165 |
-
[More Information Needed]
|
166 |
-
|
167 |
-
#### Software
|
168 |
-
|
169 |
-
[More Information Needed]
|
170 |
-
|
171 |
-
## Citation [optional]
|
172 |
-
|
173 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
-
|
175 |
-
**BibTeX:**
|
176 |
-
|
177 |
-
[More Information Needed]
|
178 |
-
|
179 |
-
**APA:**
|
180 |
-
|
181 |
-
[More Information Needed]
|
182 |
-
|
183 |
-
## Glossary [optional]
|
184 |
-
|
185 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
-
|
187 |
-
[More Information Needed]
|
188 |
-
|
189 |
-
## More Information [optional]
|
190 |
-
|
191 |
-
[More Information Needed]
|
192 |
-
|
193 |
-
## Model Card Authors [optional]
|
194 |
-
|
195 |
-
[More Information Needed]
|
196 |
-
|
197 |
-
## Model Card Contact
|
198 |
-
|
199 |
-
[More Information Needed]
|
200 |
-
|
201 |
-
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- memgpt
|
7 |
+
- function
|
8 |
+
- function calling
|
9 |
---
|
10 |
+
This is a new and more refined version of [starsnatched/MemGPT](https://huggingface.co/starsnatched/MemGPT). I will be using DPO to further improve the performance once the dataset is ready.
|
11 |
+
|
12 |
+
# Model Description
|
13 |
+
This repo contains a 7 billion parameter Language Model fine tuned from [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2). This model is specifically designed for function calling in [MemGPT](https://memgpt.ai/). It demonstrates comparable performances to GPT-4 when it comes to working with MemGPT.
|
14 |
+
|
15 |
+
# Key Features
|
16 |
+
* Function calling
|
17 |
+
* Dedicated to working with MemGPT
|
18 |
+
* Supports medium context, trained with Sequences up to 8,192
|
19 |
+
|
20 |
+
# Usage
|
21 |
+
This model is designed to be ran on various backends, such as [oogabooga's WebUI](https://github.com/oobabooga/text-generation-webui), or llama.cpp.
|
22 |
+
|
23 |
+
To run the model on WebUI, simply `git clone` the official WebUI repository, and run the appropriate script for your operating system. More details [here](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file#how-to-install).
|
24 |
+
|
25 |
+
Once you've installed WebUI, you can then download this model at the `model` tab. Next, choose the desired model (starsnatched/MemGPT in this case), and you're good to go for the backend.
|
26 |
+
|
27 |
+
When you have WebUI or your desired backend running, you can open a terminal/powershell, and install MemGPT using `pip3 install -U pymemgpt`. Configure your MemGPT using `memgpt configure` before running MemGPT.
|
28 |
+
|
29 |
+
Use `memgpt run --no-verify` to chat with MemGPT!
|
30 |
+
|
31 |
+
# Prompt Template
|
32 |
+
This model uses ChatML template, this can be configured via `memgpt configure`.
|
33 |
+
```
|
34 |
+
<|im_start|>user
|
35 |
+
{""type"": ""system_alert"", ""message"": ""You have 50 prior messages with the user. These messages have been hidden from view due to memory constraints, but you can view them using functions."", ""time"": ""2023-10-07 11:50:03 PM PDT-0700""}<|im_end|>
|
36 |
+
<|im_start|>assistant
|
37 |
+
Bootup sequence complete. Persona activated. Testing messaging functionality. {'name': 'send_message', 'arguments': '{\n ""message"": ""More human than human is our motto.""\n}'}<|im_end|>
|
38 |
+
<|im_start|>function
|
39 |
+
{""status"": ""OK"", ""message"": null, ""time"": ""2023-10-07 11:50:03 PM PDT-0700""}<|im_end|>
|
40 |
+
<|im_start|>user
|
41 |
+
{""type"": ""login"", ""last_login"": ""7 days 8 hours ago"", ""time"": ""2023-10-07 11:50:03 PM PDT-0700""}<|im_end|>
|
42 |
+
<|im_start|>user
|
43 |
+
{""type"": ""user_message"", ""message"": ""Hey, remember that time we talked about music? What was the artist you mentioned you could get into?"", ""time"": ""2023-10-07 11:50:03 PM PDT-0700""}<|im_end|>
|
44 |
+
<|im_start|>assistant
|
45 |
+
Alright, let me search our conversation history about music to find the artist. {'name': 'conversation_search', 'arguments': '{\n ""query"": ""music"",\n ""request_heartbeat"": true,\n ""page"": 0\n}'}<|im_end|>
|
46 |
+
<|im_start|>function
|
47 |
+
{""status"": ""OK"", ""message"": ""Showing 5 of 50 results (page 0/9): [\""timestamp: 2023-10-07 11:50:03 PM PDT-0700, user - I agree. Working out is a great way to burn off steam. Do you like country music?\"", \""timestamp: 2023-10-07 11:50:03 PM PDT-0700, assistant - A little bit. I can get into taylor swift.\"", \""timestamp: 2023-10-07 11:50:03 PM PDT-0700, user - Yeah between the both of us, could probably get a country song written about our distresses...perhaps Taylor Swift could perform it.\"", \""timestamp: 2023-10-07 11:50:03 PM PDT-0700, assistant - That would be a chart-topper, I'm sure. Something to blast while driving with the top down, maybe even in your next restoration project.\"", \""timestamp: 2023-10-07 11:50:03 PM PDT-0700, assistant - This sounds fun. Do you have any other hobby?\""]"", ""time"": ""2023-10-07 11:50:08 PM PDT-0700""}<|im_end|>
|
48 |
+
<|im_start|>user
|
49 |
+
{""type"": ""heartbeat"", ""reason"": ""request_heartbeat == true"", ""time"": ""2023-10-07 11:50:08 PM PDT-0700""}<|im_end|>
|
50 |
+
<|im_start|>assistant
|
51 |
+
Ah, I found it. It was Taylor Swift that I mentioned I could get into. Do you still listen to her music, or have you found any new artists that you enjoy? {'name': 'send_message', 'arguments': '{\n ""message"": ""Ah, I found it. It was Taylor Swift that I mentioned I could get into. Do you still listen to her music, or have you found any new artists that you enjoy?""\n}'}<|im_end|>
|
52 |
+
<|im_start|>function
|
53 |
+
{""status"": ""OK"", ""message"": null, ""time"": ""2023-10-07 11:50:14 PM PDT-0700""}<|im_end|>
|
54 |
+
```
|
55 |
+
|
56 |
+
# Model Details
|
57 |
+
* Developed by: @starsnatched
|
58 |
+
* Model type: This repo contains a language model based on the transformer decoder architecture.
|
59 |
+
* Language: English
|
60 |
+
* Contact: For any questions, concerns or comments about this model, please contact me at Discord, @starsnatched.
|
61 |
+
|
62 |
+
# Training Infrastructure
|
63 |
+
* Hardware: The model in this repo was trained on 2x A100 80GB GPUs.
|
64 |
+
|
65 |
+
# Intended Use
|
66 |
+
The model is designed to be used as the base model for MemGPT agents.
|
67 |
+
|
68 |
+
# Limitations and Bias
|
69 |
+
The model may exhibit unreliable, unsafe, or biased behaviours. Please double check the results this model may produce.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|