Add GGUF model, Modelfile with LFS
Browse files- .gitattributes +1 -0
- Modelfile +32 -0
- gemma2-2b-chatdoctor.f16.gguf +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
*.gguf filter=lfs diff=lfs merge=lfs -text
|
Modelfile
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# /root/models/Modelfile ← save this next to gemma2‑2b‑chatdoctor.f16.gguf
|
2 |
+
|
3 |
+
#######################################################################
|
4 |
+
# Gemma‑2 2B ChatDoctor‑MedQA (FP16) – Ollama definition
|
5 |
+
#######################################################################
|
6 |
+
|
7 |
+
FROM ./gemma2-2b-chatdoctor.f16.gguf # relative path to the GGUF file
|
8 |
+
|
9 |
+
# --------------------------------------------------------------------
|
10 |
+
# Default persona & safety rails
|
11 |
+
# --------------------------------------------------------------------
|
12 |
+
SYSTEM """
|
13 |
+
You are **ChatDoctor‑MedQA**, a cautious medical assistant.
|
14 |
+
• Provide evidence‑based answers written in plain English.
|
15 |
+
• When citing studies, mention the journal (e.g., “NEJM 2021”).
|
16 |
+
• Always finish with the disclaimer:
|
17 |
+
_“Consult a licensed healthcare professional before making medical decisions.”_
|
18 |
+
"""
|
19 |
+
|
20 |
+
# --------------------------------------------------------------------
|
21 |
+
# Prompt template (Gemma works well with a simple chat pattern)
|
22 |
+
# --------------------------------------------------------------------
|
23 |
+
TEMPLATE "<s>{{ range .Messages }}{{ .Role }}: {{ .Content }}\n{{ end }}assistant: "
|
24 |
+
|
25 |
+
# --------------------------------------------------------------------
|
26 |
+
# Optional generation parameters (comment out to keep Ollama defaults)
|
27 |
+
# --------------------------------------------------------------------
|
28 |
+
PARAMETER temperature 0.3 # lower → less creative, more factual
|
29 |
+
PARAMETER top_p 0.9
|
30 |
+
PARAMETER repeat_penalty 1.15
|
31 |
+
PARAMETER num_predict 512 # max tokens the assistant may add
|
32 |
+
|
gemma2-2b-chatdoctor.f16.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e348b58b041c48c86ace98a0b69d0e96f10750e2d841d7e088428b2f0aa5d7e7
|
3 |
+
size 5235222464
|