Update README.md
Browse files
README.md
CHANGED
@@ -10,48 +10,37 @@ language:
|
|
10 |
- en
|
11 |
base_model:
|
12 |
- HuggingFaceTB/SmolLM2-1.7B-Instruct
|
13 |
-
pipeline_tag:
|
14 |
---
|
15 |
|
16 |
-
# Model Card for
|
17 |
|
18 |
-
Kurtis
|
19 |
|
20 |
## Model Details
|
21 |
|
22 |
### Model Description
|
23 |
|
24 |
- **Developed by:** Massimo R. Scamarcia <[email protected]>
|
25 |
-
- **Funded by
|
26 |
-
- **Shared by
|
27 |
- **Model type:** Transformer decoder
|
28 |
- **Language(s) (NLP):** English
|
29 |
- **License:** MIT
|
30 |
-
- **Finetuned from model
|
31 |
|
32 |
-
### Model Sources
|
33 |
-
|
34 |
-
<!-- Provide the basic links for the model. -->
|
35 |
|
36 |
- **Repository:** [https://github.com/mrs83/kurtis](https://github.com/mrs83/kurtis)
|
37 |
-
- **Paper [optional]:** None
|
38 |
-
- **Demo [optional]:** [More Information Needed]
|
39 |
|
40 |
## Uses
|
41 |
|
42 |
-
The model is intended for use in a conversational setting, particularly in mental health and therapeutic support scenarios.
|
43 |
-
|
44 |
-
Suitable use cases include:
|
45 |
-
|
46 |
-
- Evaluating the usage of small-language models (SLMs).
|
47 |
-
- Evaluating small-language models (SLMs) capability to generate empathetic responses in a mental-health context.
|
48 |
-
|
49 |
|
50 |
### Direct Use
|
51 |
|
52 |
Not suitable for production usage.
|
53 |
|
54 |
-
|
55 |
### Out-of-Scope Use
|
56 |
|
57 |
This model should not be used for:
|
@@ -61,99 +50,14 @@ This model should not be used for:
|
|
61 |
- Applications where responses require regulatory compliance or are highly sensitive.
|
62 |
- Generating responses without human supervision, especially in contexts that involve vulnerable individuals.
|
63 |
|
64 |
-
|
65 |
## Bias, Risks, and Limitations
|
66 |
|
67 |
Misuse of this dataset could lead to providing inappropriate or harmful responses, so it should not be deployed without proper safeguards in place.
|
68 |
|
69 |
### Recommendations
|
70 |
|
71 |
-
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
|
72 |
|
73 |
## How to Get Started with the Model
|
74 |
|
75 |
-
|
76 |
-
|
77 |
-
[More Information Needed]
|
78 |
-
|
79 |
-
## Training Details
|
80 |
-
|
81 |
-
### Training Data
|
82 |
-
|
83 |
-
WIP
|
84 |
-
|
85 |
-
[More Information Needed]
|
86 |
-
|
87 |
-
### Training Procedure
|
88 |
-
|
89 |
-
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
90 |
-
|
91 |
-
#### Preprocessing [optional]
|
92 |
-
|
93 |
-
[More Information Needed]
|
94 |
-
|
95 |
-
|
96 |
-
#### Training Hyperparameters
|
97 |
-
|
98 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
99 |
-
|
100 |
-
#### Speeds, Sizes, Times [optional]
|
101 |
-
|
102 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
103 |
-
|
104 |
-
[More Information Needed]
|
105 |
-
|
106 |
-
## Evaluation
|
107 |
-
|
108 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
109 |
-
|
110 |
-
### Testing Data, Factors & Metrics
|
111 |
-
|
112 |
-
#### Testing Data
|
113 |
-
|
114 |
-
<!-- This should link to a Dataset Card if possible. -->
|
115 |
-
|
116 |
-
[More Information Needed]
|
117 |
-
|
118 |
-
#### Factors
|
119 |
-
|
120 |
-
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
121 |
-
|
122 |
-
[More Information Needed]
|
123 |
-
|
124 |
-
#### Metrics
|
125 |
-
|
126 |
-
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
127 |
-
|
128 |
-
[More Information Needed]
|
129 |
-
|
130 |
-
### Results
|
131 |
-
|
132 |
-
[More Information Needed]
|
133 |
-
|
134 |
-
#### Summary
|
135 |
-
|
136 |
-
|
137 |
-
|
138 |
-
## Technical Specifications [optional]
|
139 |
-
|
140 |
-
### Model Architecture and Objective
|
141 |
-
|
142 |
-
[More Information Needed]
|
143 |
-
|
144 |
-
### Compute Infrastructure
|
145 |
-
|
146 |
-
[More Information Needed]
|
147 |
-
|
148 |
-
#### Hardware
|
149 |
-
|
150 |
-
[More Information Needed]
|
151 |
-
|
152 |
-
#### Software
|
153 |
-
|
154 |
-
[More Information Needed]
|
155 |
-
|
156 |
-
|
157 |
-
## Model Card Contact
|
158 |
-
|
159 |
-
Massimo R. Scamarcia <[email protected]>
|
|
|
10 |
- en
|
11 |
base_model:
|
12 |
- HuggingFaceTB/SmolLM2-1.7B-Instruct
|
13 |
+
pipeline_tag: text-generation
|
14 |
---
|
15 |
|
16 |
+
# Model Card for Kurtis-SmolLM2-1.7B-Instruct
|
17 |
|
18 |
+
This model has been fine-tuned using Kurtis, an experimental fine-tuning, inference and evaluation tool for Small Language Models.
|
19 |
|
20 |
## Model Details
|
21 |
|
22 |
### Model Description
|
23 |
|
24 |
- **Developed by:** Massimo R. Scamarcia <[email protected]>
|
25 |
+
- **Funded by:** Massimo R. Scamarcia <[email protected]> - (self-funded)
|
26 |
+
- **Shared by:** Massimo R. Scamarcia <[email protected]>
|
27 |
- **Model type:** Transformer decoder
|
28 |
- **Language(s) (NLP):** English
|
29 |
- **License:** MIT
|
30 |
+
- **Finetuned from model:** HuggingFaceTB/SmolLM2-1.7B-Instruct
|
31 |
|
32 |
+
### Model Sources
|
|
|
|
|
33 |
|
34 |
- **Repository:** [https://github.com/mrs83/kurtis](https://github.com/mrs83/kurtis)
|
|
|
|
|
35 |
|
36 |
## Uses
|
37 |
|
38 |
+
The model is intended for use in a conversational setting, particularly in mental health and therapeutic support scenarios.
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
|
40 |
### Direct Use
|
41 |
|
42 |
Not suitable for production usage.
|
43 |
|
|
|
44 |
### Out-of-Scope Use
|
45 |
|
46 |
This model should not be used for:
|
|
|
50 |
- Applications where responses require regulatory compliance or are highly sensitive.
|
51 |
- Generating responses without human supervision, especially in contexts that involve vulnerable individuals.
|
52 |
|
|
|
53 |
## Bias, Risks, and Limitations
|
54 |
|
55 |
Misuse of this dataset could lead to providing inappropriate or harmful responses, so it should not be deployed without proper safeguards in place.
|
56 |
|
57 |
### Recommendations
|
58 |
|
59 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model.
|
60 |
|
61 |
## How to Get Started with the Model
|
62 |
|
63 |
+
WIP
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|