limcheekin commited on
Commit
034433d
1 Parent(s): a525bd4

feat: updated to IS-LM-3B_GGUF model

Browse files
Files changed (4) hide show
  1. Dockerfile +1 -1
  2. README.md +5 -5
  3. index.html +6 -6
  4. main.py +1 -2
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/UmbrellaCorp/IS-LM-3B_GGUF/resolve/main/IS-LM-f16.gguf -o model/gguf-model.bin
19
 
20
  COPY ./start_server.sh ./
21
  COPY ./main.py ./
README.md CHANGED
@@ -1,20 +1,20 @@
1
  ---
2
- title: replit-code-v1_5-3b-GGUF (F16)
3
  colorFrom: purple
4
  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
12
  - llama-cpp-python
13
- - replit-code-v1_5-3b-GGUF
14
  - gguf
15
  pinned: false
16
  ---
17
 
18
- # replit-code-v1_5-3b-GGUF (F16)
19
 
20
  Please refer to the [index.html](index.html) for more information.
 
1
  ---
2
+ title: IS-LM-3B_GGUF (F16)
3
  colorFrom: purple
4
  colorTo: blue
5
  sdk: docker
6
  models:
7
+ - acrastt/IS-LM-3B
8
+ - UmbrellaCorp/IS-LM-3B_GGUF
9
  tags:
10
  - inference api
11
  - openai-api compatible
12
  - llama-cpp-python
13
+ - IS-LM-3B_GGUF
14
  - gguf
15
  pinned: false
16
  ---
17
 
18
+ # IS-LM-3B_GGUF (F16)
19
 
20
  Please refer to the [index.html](index.html) for more information.
index.html CHANGED
@@ -1,10 +1,10 @@
1
  <!DOCTYPE html>
2
  <html>
3
  <head>
4
- <title>replit-code-v1_5-3b-GGUF (F16)</title>
5
  </head>
6
  <body>
7
- <h1>replit-code-v1_5-3b-GGUF (F16)</h1>
8
  <p>
9
  With the utilization of the
10
  <a href="https://github.com/abetlen/llama-cpp-python">llama-cpp-python</a>
@@ -16,14 +16,14 @@
16
  <ul>
17
  <li>
18
  The API endpoint:
19
- <a href="https://limcheekin-replit-code-v1-5-3b-gguf.hf.space/v1"
20
- >https://limcheekin-replit-code-v1-5-3b-gguf.hf.space/v1</a
21
  >
22
  </li>
23
  <li>
24
  The API doc:
25
- <a href="https://limcheekin-replit-code-v1-5-3b-gguf.hf.space/docs"
26
- >https://limcheekin-replit-code-v1-5-3b-gguf.hf.space/docs</a
27
  >
28
  </li>
29
  </ul>
 
1
  <!DOCTYPE html>
2
  <html>
3
  <head>
4
+ <title>IS-LM-3B_GGUF (F16)</title>
5
  </head>
6
  <body>
7
+ <h1>IS-LM-3B_GGUF (F16)</h1>
8
  <p>
9
  With the utilization of the
10
  <a href="https://github.com/abetlen/llama-cpp-python">llama-cpp-python</a>
 
16
  <ul>
17
  <li>
18
  The API endpoint:
19
+ <a href="https://limcheekin-is-lm-3b-gguf.hf.space/v1"
20
+ >https://limcheekin-is-lm-3b-gguf.hf.space/v1</a
21
  >
22
  </li>
23
  <li>
24
  The API doc:
25
+ <a href="https://limcheekin-is-lm-3b-gguf.hf.space/docs"
26
+ >https://limcheekin-is-lm-3b-gguf.hf.space/docs</a
27
  >
28
  </li>
29
  </ul>
main.py CHANGED
@@ -6,8 +6,7 @@ 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
- n_ctx=16192 # For GitHub Copilot
11
  )
12
  )
13
 
 
6
  Settings(
7
  n_threads=2, # set to number of cpu cores
8
  model="model/gguf-model.bin",
9
+ embedding=True
 
10
  )
11
  )
12