fabrizziomcl commited on
Commit
83ebd41
·
verified ·
1 Parent(s): de24331

Point Space to org-hosted model build-small-hackathon/educrate-qwen3-sft

Browse files
Files changed (3) hide show
  1. .gitignore +2 -0
  2. README.md +2 -2
  3. app.py +1 -1
.gitignore ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ __pycache__/
2
+ *.pyc
README.md CHANGED
@@ -20,7 +20,7 @@ tags:
20
  - achievement:offbrand
21
  - sponsor:modal
22
  models:
23
- - fabrizziomcl/nanoballena-qwen3-sft
24
  - fabrizziomcl/nanoballena-qwen3-socratic
25
  ---
26
 
@@ -34,7 +34,7 @@ reasoning and reading comprehension, small enough to run on CPU.
34
  ## Links
35
  - Demo video: _TODO: paste link_
36
  - Social post: _TODO: paste link_
37
- - Model: https://huggingface.co/fabrizziomcl/nanoballena-qwen3-sft
38
 
39
  ## The problem
40
  Peru's public secondary schools face a learning crisis. In PISA 2022 (OECD), only 34%
 
20
  - achievement:offbrand
21
  - sponsor:modal
22
  models:
23
+ - build-small-hackathon/educrate-qwen3-sft
24
  - fabrizziomcl/nanoballena-qwen3-socratic
25
  ---
26
 
 
34
  ## Links
35
  - Demo video: _TODO: paste link_
36
  - Social post: _TODO: paste link_
37
+ - Model: https://huggingface.co/build-small-hackathon/educrate-qwen3-sft
38
 
39
  ## The problem
40
  Peru's public secondary schools face a learning crisis. In PISA 2022 (OECD), only 34%
app.py CHANGED
@@ -10,7 +10,7 @@ import os
10
  import gradio as gr
11
  import torch
12
 
13
- MODEL_ID = os.environ.get("MODEL_ID", "fabrizziomcl/nanoballena-qwen3-sft")
14
  MAX_TURNS = int(os.environ.get("MAX_TURNS", "8"))
15
  DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
16
  DTYPE = torch.bfloat16 if DEVICE == "cuda" else torch.float32
 
10
  import gradio as gr
11
  import torch
12
 
13
+ MODEL_ID = os.environ.get("MODEL_ID", "build-small-hackathon/educrate-qwen3-sft")
14
  MAX_TURNS = int(os.environ.get("MAX_TURNS", "8"))
15
  DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
16
  DTYPE = torch.bfloat16 if DEVICE == "cuda" else torch.float32