Update README.md
Browse files
README.md
CHANGED
@@ -24,6 +24,13 @@ MedleyMD is a Mixure of Experts (MoE) made with the following models using [Lazy
|
|
24 |
|
25 |
These models were chosen because `fblgit/UNA-TheBeagle-7b-v1` has excellent performance for a 7B parameter model and Dr.Samantha has capabilities of a medical knowledge-focused model (trained on USMLE databases and doctor-patient interactions) with the philosophical, psychological, and relational understanding, scoring 68.82% in topics related to clinical domain and psychology.
|
26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
27 |
## 🧩 Configuration
|
28 |
|
29 |
```yaml
|
@@ -41,15 +48,13 @@ experts:
|
|
41 |
```
|
42 |
|
43 |
## GGUF
|
44 |
-
GGUF is available to download.
|
45 |
1. [medleymd.Q4_K_M](https://huggingface.co/sethuiyer/MedleyMD-GGUF/resolve/main/medleymd.Q4_K_M.gguf) [7.2GB]
|
46 |
2. [medleymd.Q5_K_M](https://huggingface.co/sethuiyer/MedleyMD-GGUF/resolve/main/medleymd.Q5_K_M.gguf) [9.13GB]
|
47 |
|
48 |
|
49 |
## Ollama
|
50 |
|
51 |
-
MedleyMD
|
52 |
-
terminal.
|
53 |
|
54 |
If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on
|
55 |
a Google Colab backend.
|
|
|
24 |
|
25 |
These models were chosen because `fblgit/UNA-TheBeagle-7b-v1` has excellent performance for a 7B parameter model and Dr.Samantha has capabilities of a medical knowledge-focused model (trained on USMLE databases and doctor-patient interactions) with the philosophical, psychological, and relational understanding, scoring 68.82% in topics related to clinical domain and psychology.
|
26 |
|
27 |
+
## Benchmark
|
28 |
+
|
29 |
+
On a synthetic benchmark of 15 medical diagnosis questions generated by GPT-4, GPT-4 also being an evaluator, MedleyMD scored 94.25/100.
|
30 |
+
|
31 |
+
Nous Benchmark numbers shall be available soon.
|
32 |
+
|
33 |
+
|
34 |
## 🧩 Configuration
|
35 |
|
36 |
```yaml
|
|
|
48 |
```
|
49 |
|
50 |
## GGUF
|
|
|
51 |
1. [medleymd.Q4_K_M](https://huggingface.co/sethuiyer/MedleyMD-GGUF/resolve/main/medleymd.Q4_K_M.gguf) [7.2GB]
|
52 |
2. [medleymd.Q5_K_M](https://huggingface.co/sethuiyer/MedleyMD-GGUF/resolve/main/medleymd.Q5_K_M.gguf) [9.13GB]
|
53 |
|
54 |
|
55 |
## Ollama
|
56 |
|
57 |
+
MedleyMD can be used in ollama by running```ollama run stuehieyr/medleymd``` in your terminal.
|
|
|
58 |
|
59 |
If you have limited computing resources, check out this [video](https://www.youtube.com/watch?v=Qa1h7ygwQq8) to learn how to run it on
|
60 |
a Google Colab backend.
|