Instructions to use NeoDim/starcoder-GGML with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NeoDim/starcoder-GGML with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="NeoDim/starcoder-GGML")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("NeoDim/starcoder-GGML", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use NeoDim/starcoder-GGML with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "NeoDim/starcoder-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/starcoder-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/NeoDim/starcoder-GGML
- SGLang
How to use NeoDim/starcoder-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/starcoder-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/starcoder-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/starcoder-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/starcoder-GGML", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use NeoDim/starcoder-GGML with Docker Model Runner:
docker model run hf.co/NeoDim/starcoder-GGML
Sergey Kostyaev commited on
Commit ·
4a10c50
1
Parent(s): b9b9229
Requantize models
Browse filesRequantize models after ggml update
- starcoder-ggml-q4_0.bin +2 -2
- starcoder-ggml-q4_1.bin +2 -2
- starcoder-ggml-q5_0.bin +1 -1
- starcoder-ggml-q5_1.bin +1 -1
- starcoder-ggml-q8_0.bin +2 -2
starcoder-ggml-q4_0.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:beac3071072969b960c25cf56d81109d2a1a81465c7ab80a62d88ef33db1cef7
|
| 3 |
+
size 10746563472
|
starcoder-ggml-q4_1.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c75c15b5a1faa24ea839cbfb20a6ac6be4d650382f067ea01c96fc9d07482320
|
| 3 |
+
size 11916774288
|
starcoder-ggml-q5_0.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13086985104
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2494878d1c4867677b6d068c00a9c7e6b312436ccf0213f1b913c21711eae239
|
| 3 |
size 13086985104
|
starcoder-ggml-q5_1.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14257195920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2f4827e7c9b2a025ebe7931ade7b5de100d31e6f030a362bfeb2af89c4d2230
|
| 3 |
size 14257195920
|
starcoder-ggml-q8_0.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:769af86544e37e52fbcbd99552448fc6eb695e440fca0303535db09cd242065d
|
| 3 |
+
size 20108250000
|