Update README.md
Browse files
README.md
CHANGED
@@ -9,6 +9,59 @@ base_model:
|
|
9 |
pipeline_tag: text-generation
|
10 |
---
|
11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
```
|
13 |
ollama run hf.co/mrs83/Kurtis-SmolLM2-360M-Instruct-GGUF
|
14 |
```
|
|
|
9 |
pipeline_tag: text-generation
|
10 |
---
|
11 |
|
12 |
+
|
13 |
+
# Model Card for Model ID
|
14 |
+
|
15 |
+
This model has been fine-tuned using Kurtis, an experimental fine-tuning, inference and evaluation tool for Small Language Models.
|
16 |
+
|
17 |
+
## Model Details
|
18 |
+
|
19 |
+
### Model Description
|
20 |
+
|
21 |
+
- **Developed by:** Massimo R. Scamarcia <massimo.scamarcia@gmail.com>
|
22 |
+
- **Funded by:** Massimo R. Scamarcia <massimo.scamarcia@gmail.com> - (self-funded)
|
23 |
+
- **Shared by:** Massimo R. Scamarcia <massimo.scamarcia@gmail.com>
|
24 |
+
- **Model type:** Transformer decoder
|
25 |
+
- **Language(s) (NLP):** English
|
26 |
+
- **License:** MIT
|
27 |
+
- **Finetuned from model [optional]:** HuggingFaceTB/SmolLM2-360M-Instruct
|
28 |
+
|
29 |
+
### Model Sources
|
30 |
+
|
31 |
+
- **Repository:** [https://github.com/mrs83/kurtis](https://github.com/mrs83/kurtis)
|
32 |
+
|
33 |
+
## Uses
|
34 |
+
|
35 |
+
The model is intended for use in a conversational setting, particularly in mental health and therapeutic support scenarios.
|
36 |
+
|
37 |
+
Suitable use cases include:
|
38 |
+
|
39 |
+
- Evaluating the usage of small-language models (SLMs).
|
40 |
+
- Evaluating small-language models (SLMs) capability to generate empathetic responses in a mental-health context.
|
41 |
+
|
42 |
+
### Direct Use
|
43 |
+
|
44 |
+
Not suitable for production usage.
|
45 |
+
|
46 |
+
### Out-of-Scope Use
|
47 |
+
|
48 |
+
This model should not be used for:
|
49 |
+
|
50 |
+
- Making critical mental health decisions or diagnoses.
|
51 |
+
- Replacing professional mental health services.
|
52 |
+
- Applications where responses require regulatory compliance or are highly sensitive.
|
53 |
+
- Generating responses without human supervision, especially in contexts that involve vulnerable individuals.
|
54 |
+
|
55 |
+
## Bias, Risks, and Limitations
|
56 |
+
|
57 |
+
Misuse of this dataset could lead to providing inappropriate or harmful responses, so it should not be deployed without proper safeguards in place.
|
58 |
+
|
59 |
+
### Recommendations
|
60 |
+
|
61 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
62 |
+
|
63 |
+
## How to Get Started with the Model
|
64 |
+
|
65 |
```
|
66 |
ollama run hf.co/mrs83/Kurtis-SmolLM2-360M-Instruct-GGUF
|
67 |
```
|