Instructions to use MalikIbrar/flan-python-expert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MalikIbrar/flan-python-expert with Transformers:

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

pipe = pipeline("text-generation", model="MalikIbrar/flan-python-expert")

# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("MalikIbrar/flan-python-expert")
model = AutoModelForSeq2SeqLM.from_pretrained("MalikIbrar/flan-python-expert")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use MalikIbrar/flan-python-expert with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MalikIbrar/flan-python-expert

SGLang

How to use MalikIbrar/flan-python-expert 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 "MalikIbrar/flan-python-expert" \
    --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": "MalikIbrar/flan-python-expert",
		"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 "MalikIbrar/flan-python-expert" \
        --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": "MalikIbrar/flan-python-expert",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use MalikIbrar/flan-python-expert with Docker Model Runner:
```
docker model run hf.co/MalikIbrar/flan-python-expert
```

MalikIbrar commited on Apr 9, 2025

Commit

c634cb3

verified ·

1 Parent(s): ebb7e65

Upload tokenizer

Browse files

Files changed (1) hide show

tokenizer_config.json +8 -0

tokenizer_config.json CHANGED Viewed

@@ -1,4 +1,5 @@
 {
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",
@@ -931,9 +932,16 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "extra_special_tokens": {},
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",
   "unk_token": "<unk>"
 }

 {
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<pad>",
   "eos_token": "</s>",
   "extra_ids": 100,
   "extra_special_tokens": {},
+  "max_length": 1024,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
   "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sp_model_kwargs": {},
+  "stride": 0,
   "tokenizer_class": "T5Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "<unk>"
 }