limcheekin commited on
Commit
3cfa708
1 Parent(s): 2a40a34

feat: updated model download url and n_ctx param

Browse files
Files changed (3) hide show
  1. Dockerfile +1 -1
  2. README.md +1 -1
  3. main.py +2 -1
Dockerfile CHANGED
@@ -15,7 +15,7 @@ RUN pip install -U pip setuptools wheel && \
15
 
16
  # Download model
17
  RUN mkdir model && \
18
- curl -L https://huggingface.co/lynnleelhl/replit-code-v1_5-3b-gguf/resolve/main/ggml-model-f16.gguf -o model/gguf-model.bin
19
 
20
  COPY ./start_server.sh ./
21
  COPY ./main.py ./
 
15
 
16
  # Download model
17
  RUN mkdir model && \
18
+ curl -L https://huggingface.co/abetlen/replit-code-v1_5-3b-GGUF/resolve/main/replit-code-v1_5-3b.f16.gguf -o model/gguf-model.bin
19
 
20
  COPY ./start_server.sh ./
21
  COPY ./main.py ./
README.md CHANGED
@@ -5,7 +5,7 @@ colorTo: blue
5
  sdk: docker
6
  models:
7
  - replit/replit-code-v1_5-3b
8
- - lynnleelhl/replit-code-v1_5-3b-gguf
9
  tags:
10
  - inference api
11
  - openai-api compatible
 
5
  sdk: docker
6
  models:
7
  - replit/replit-code-v1_5-3b
8
+ - abetlen/replit-code-v1_5-3b-GGUF
9
  tags:
10
  - inference api
11
  - openai-api compatible
main.py CHANGED
@@ -6,7 +6,8 @@ app = create_app(
6
  Settings(
7
  n_threads=2, # set to number of cpu cores
8
  model="model/gguf-model.bin",
9
- embedding=True
 
10
  )
11
  )
12
 
 
6
  Settings(
7
  n_threads=2, # set to number of cpu cores
8
  model="model/gguf-model.bin",
9
+ embedding=True,
10
+ n_ctx=16192 # For GitHub Copilot
11
  )
12
  )
13