Instructions to use FelixChao/vicuna-33b-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FelixChao/vicuna-33b-coder with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="FelixChao/vicuna-33b-coder")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FelixChao/vicuna-33b-coder")
model = AutoModelForCausalLM.from_pretrained("FelixChao/vicuna-33b-coder")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FelixChao/vicuna-33b-coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FelixChao/vicuna-33b-coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FelixChao/vicuna-33b-coder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FelixChao/vicuna-33b-coder

SGLang

How to use FelixChao/vicuna-33b-coder 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 "FelixChao/vicuna-33b-coder" \
    --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": "FelixChao/vicuna-33b-coder",
		"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 "FelixChao/vicuna-33b-coder" \
        --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": "FelixChao/vicuna-33b-coder",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FelixChao/vicuna-33b-coder with Docker Model Runner:
```
docker model run hf.co/FelixChao/vicuna-33b-coder
```

FelixChao commited on Sep 11, 2023

Commit

6a09cc9

1 Parent(s): 9db56ad

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -4

README.md CHANGED Viewed

@@ -6,14 +6,15 @@ model-index:
 - name: Vicuna-Coder
   results:
   - task:
-      type: Code-generation             # Required. Example: automatic-speech-recognition
     dataset:
-      type: python          # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
-      name: HumanEval          # Required. A pretty name for the dataset. Example: Common Voice (French)
     metrics:
-      - type: pass@k         # Required. Example: wer. Use metric id from https://hf.co/metrics
         value: 0.274       # Required. Example: 20.90
         name: pass@1         # Optional. Example: Test WER
 ---
 ---
 # Model Card for Model ID

 - name: Vicuna-Coder
   results:
   - task:
+      type: text-generation             # Required. Example: automatic-speech-recognition
     dataset:
+      type: nuprl/MultiPL-E         # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
+      name: MultiPL-HumanEval (Python)          # Required. A pretty name for the dataset. Example: Common Voice (French)
     metrics:
+      - type: pass@1         # Required. Example: wer. Use metric id from https://hf.co/metrics
         value: 0.274       # Required. Example: 20.90
         name: pass@1         # Optional. Example: Test WER
+        verified: false
 ---
 ---
 # Model Card for Model ID