Instructions to use NeoDim/starcoderbase-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NeoDim/starcoderbase-GGML with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NeoDim/starcoderbase-GGML")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("NeoDim/starcoderbase-GGML", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use NeoDim/starcoderbase-GGML with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NeoDim/starcoderbase-GGML" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NeoDim/starcoderbase-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NeoDim/starcoderbase-GGML
- SGLang
How to use NeoDim/starcoderbase-GGML with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "NeoDim/starcoderbase-GGML" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NeoDim/starcoderbase-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "NeoDim/starcoderbase-GGML" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "NeoDim/starcoderbase-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NeoDim/starcoderbase-GGML with Docker Model Runner:
docker model run hf.co/NeoDim/starcoderbase-GGML
Sergey Kostyaev commited on
Commit ·
e6ff521
1
Parent(s): 66a5b0f
Add models
Browse filesAdd ggml models
- starcoderbase-ggml-f16.bin +3 -0
- starcoderbase-ggml-q4_0.bin +3 -0
- starcoderbase-ggml-q4_1.bin +3 -0
- starcoderbase-ggml-q5_0.bin +3 -0
- starcoderbase-ggml-q5_1.bin +3 -0
- starcoderbase-ggml-q8_0.bin +3 -0
starcoderbase-ggml-f16.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dfa7f7f7783738983243aad8e6ce273c6416cc8dd026651c893219142027799
|
| 3 |
+
size 37661412240
|
starcoderbase-ggml-q4_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e5bcad4f976d904fc8f00e6cc53cb98dd3373a844ab9952a05b1a8f4fcfdf7e
|
| 3 |
+
size 11916774288
|
starcoderbase-ggml-q4_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab14d1fcfdb022fea06aa2afad71edf020b3aa64ec400caf637cc0584dd7d12e
|
| 3 |
+
size 14257195920
|
starcoderbase-ggml-q5_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a7025e5ee3f87cd4a9b11ff005a7a2a3576ca230cac510840229bb3ba654b75
|
| 3 |
+
size 13086985104
|
starcoderbase-ggml-q5_1.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddc45a61045398f83078b28d846ee422f4a474ff7a02ace63b36bc376160a428
|
| 3 |
+
size 14257195920
|
starcoderbase-ggml-q8_0.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dd001643dc10fc484bf8a2bb220a76478929d32dad7f6e7e7283b0d31aa17b6
|
| 3 |
+
size 21278460816
|