Instructions to use Mxode/Pythia-70m-C-Language-KnowledgeExtract with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mxode/Pythia-70m-C-Language-KnowledgeExtract with Transformers:

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

pipe = pipeline("text-generation", model="Mxode/Pythia-70m-C-Language-KnowledgeExtract")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Mxode/Pythia-70m-C-Language-KnowledgeExtract")
model = AutoModelForCausalLM.from_pretrained("Mxode/Pythia-70m-C-Language-KnowledgeExtract", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Mxode/Pythia-70m-C-Language-KnowledgeExtract with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Mxode/Pythia-70m-C-Language-KnowledgeExtract"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Mxode/Pythia-70m-C-Language-KnowledgeExtract",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Mxode/Pythia-70m-C-Language-KnowledgeExtract

SGLang

How to use Mxode/Pythia-70m-C-Language-KnowledgeExtract 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 "Mxode/Pythia-70m-C-Language-KnowledgeExtract" \
    --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": "Mxode/Pythia-70m-C-Language-KnowledgeExtract",
		"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 "Mxode/Pythia-70m-C-Language-KnowledgeExtract" \
        --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": "Mxode/Pythia-70m-C-Language-KnowledgeExtract",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Mxode/Pythia-70m-C-Language-KnowledgeExtract with Docker Model Runner:
```
docker model run hf.co/Mxode/Pythia-70m-C-Language-KnowledgeExtract
```

Mxode commited on Oct 5, 2023

Commit

a4d4ad6

1 Parent(s): ad7a79a

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -3

README.md CHANGED Viewed

@@ -23,7 +23,8 @@ device = 'cuda'
 model = GPTNeoXForCausalLM.from_pretrained(model_name_or_path).to(device)
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
-instruction = '[Summarize the knowledge points in the code below]\n'		# instruction template
 # any c-lang pieces you like, could be partial functions or statements
 input_content = '''```c
 int partition(int arr[], int low, int high) {
@@ -78,7 +79,7 @@ for i in range(30):		# maybe 20 times or less enough too
         pad_token_id=tokenizer.eos_token_id,
         max_new_tokens=32,
         do_sample=True,
-        temperature=2.0,                       # high temperature for diversity
         top_p=0.95,
         top_k=30,
     )
@@ -87,5 +88,11 @@ for i in range(30):		# maybe 20 times or less enough too
 print(ans_dict)
 ### output as below, could take high-freq answers
-### {'Backtracking': 1, 'Heap': 1, 'Quick sort': 25, 'Recurrence': 2, 'Queue': 1}
 ```

 model = GPTNeoXForCausalLM.from_pretrained(model_name_or_path).to(device)
 tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
+# instruction template
+instruction = '[Summarize the knowledge points in the code below]\n'
 # any c-lang pieces you like, could be partial functions or statements
 input_content = '''```c
 int partition(int arr[], int low, int high) {
         pad_token_id=tokenizer.eos_token_id,
         max_new_tokens=32,
         do_sample=True,
+        temperature=2.0,  # high temperature for diversity
         top_p=0.95,
         top_k=30,
     )
 print(ans_dict)
 ### output as below, could take high-freq answers
+### {
+###     'Backtracking': 1,
+###     'Heap': 1,
+###     'Quick sort': 25,
+###     'Recurrence': 2,
+###     'Queue': 1
+###}
 ```