Instructions to use cuijian0819/gpt-oss-20b-function-calling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cuijian0819/gpt-oss-20b-function-calling with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="cuijian0819/gpt-oss-20b-function-calling") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("cuijian0819/gpt-oss-20b-function-calling", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use cuijian0819/gpt-oss-20b-function-calling with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "cuijian0819/gpt-oss-20b-function-calling" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cuijian0819/gpt-oss-20b-function-calling", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/cuijian0819/gpt-oss-20b-function-calling
- SGLang
How to use cuijian0819/gpt-oss-20b-function-calling 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 "cuijian0819/gpt-oss-20b-function-calling" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cuijian0819/gpt-oss-20b-function-calling", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'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 "cuijian0819/gpt-oss-20b-function-calling" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "cuijian0819/gpt-oss-20b-function-calling", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use cuijian0819/gpt-oss-20b-function-calling with Docker Model Runner:
docker model run hf.co/cuijian0819/gpt-oss-20b-function-calling
Add PyTorch model files
Browse files
README.md
CHANGED
|
@@ -1,100 +1,58 @@
|
|
| 1 |
---
|
| 2 |
-
tags:
|
| 3 |
-
- pytorch
|
| 4 |
-
- safetensors
|
| 5 |
-
- transformers
|
| 6 |
-
- gpt-oss
|
| 7 |
-
- multilingual
|
| 8 |
-
- text-generation
|
| 9 |
-
language:
|
| 10 |
-
- en
|
| 11 |
-
- es
|
| 12 |
-
- fr
|
| 13 |
-
- de
|
| 14 |
-
- it
|
| 15 |
-
- pt
|
| 16 |
-
license: apache-2.0
|
| 17 |
-
model_type: gpt-oss
|
| 18 |
-
pipeline_tag: text-generation
|
| 19 |
base_model: openai/gpt-oss-20b
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
---
|
| 21 |
|
| 22 |
-
#
|
| 23 |
-
|
| 24 |
-
This repository contains the GPT-OSS-20B model fine-tuned on function calling data in PyTorch/Safetensors format, ready for use with the Transformers library.
|
| 25 |
-
|
| 26 |
-
## Model Details
|
| 27 |
-
|
| 28 |
-
- **Base Model:** openai/gpt-oss-20b
|
| 29 |
-
- **Fine-tuning Dataset:** Salesforce/xlam-function-calling-60k (2000 samples)
|
| 30 |
-
- **Fine-tuning Method:** LoRA (r=8, alpha=16)
|
| 31 |
-
- **Context Length:** 131,072 tokens
|
| 32 |
-
- **Model Size:** 20B parameters
|
| 33 |
-
|
| 34 |
-
## Files
|
| 35 |
-
|
| 36 |
-
- `model.safetensors`: Model weights in Safetensors format
|
| 37 |
-
- `config.json`: Model configuration
|
| 38 |
-
- `tokenizer.json`, `tokenizer_config.json`: Tokenizer files
|
| 39 |
-
- `generation_config.json`: Generation configuration
|
| 40 |
|
| 41 |
-
|
|
|
|
| 42 |
|
| 43 |
-
##
|
| 44 |
|
| 45 |
```python
|
| 46 |
-
from transformers import
|
| 47 |
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
device_map="auto"
|
| 53 |
-
)
|
| 54 |
-
tokenizer = AutoTokenizer.from_pretrained("cuijian0819/gpt-oss-20b-function-calling")
|
| 55 |
-
|
| 56 |
-
# Generate text
|
| 57 |
-
inputs = tokenizer("Your prompt here", return_tensors="pt")
|
| 58 |
-
outputs = model.generate(**inputs, max_length=100, temperature=0.7)
|
| 59 |
-
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
| 60 |
```
|
| 61 |
|
| 62 |
-
##
|
| 63 |
-
|
| 64 |
-
This model can be further fine-tuned using standard PyTorch/Transformers workflows:
|
| 65 |
|
| 66 |
-
|
| 67 |
-
from transformers import AutoModelForCausalLM, AutoTokenizer, Trainer, TrainingArguments
|
| 68 |
|
| 69 |
-
model = AutoModelForCausalLM.from_pretrained("cuijian0819/gpt-oss-20b-function-calling")
|
| 70 |
-
tokenizer = AutoTokenizer.from_pretrained("cuijian0819/gpt-oss-20b-function-calling")
|
| 71 |
|
| 72 |
-
|
| 73 |
-
```
|
| 74 |
|
| 75 |
-
##
|
| 76 |
|
| 77 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
|
| 79 |
-
##
|
| 80 |
|
| 81 |
-
- **Training Epochs:** 2
|
| 82 |
-
- **Learning Rate:** 0.0002
|
| 83 |
-
- **Batch Size:** 4
|
| 84 |
-
- **Gradient Accumulation:** 4
|
| 85 |
-
- **Max Length:** 1024
|
| 86 |
|
| 87 |
-
## License
|
| 88 |
-
|
| 89 |
-
This model inherits the license from the base openai/gpt-oss-20b model.
|
| 90 |
-
|
| 91 |
-
## Citation
|
| 92 |
|
|
|
|
|
|
|
| 93 |
```bibtex
|
| 94 |
-
@misc{
|
| 95 |
-
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
|
|
|
|
|
|
| 99 |
}
|
| 100 |
-
```
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model: openai/gpt-oss-20b
|
| 3 |
+
library_name: transformers
|
| 4 |
+
model_name: fine_tuned
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- trl
|
| 8 |
+
- sft
|
| 9 |
+
licence: license
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Model Card for fine_tuned
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [openai/gpt-oss-20b](https://huggingface.co/openai/gpt-oss-20b).
|
| 15 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 16 |
|
| 17 |
+
## Quick start
|
| 18 |
|
| 19 |
```python
|
| 20 |
+
from transformers import pipeline
|
| 21 |
|
| 22 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 23 |
+
generator = pipeline("text-generation", model="cuijian0819/fine_tuned", device="cuda")
|
| 24 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 25 |
+
print(output["generated_text"])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
```
|
| 27 |
|
| 28 |
+
## Training procedure
|
|
|
|
|
|
|
| 29 |
|
| 30 |
+
|
|
|
|
| 31 |
|
|
|
|
|
|
|
| 32 |
|
| 33 |
+
This model was trained with SFT.
|
|
|
|
| 34 |
|
| 35 |
+
### Framework versions
|
| 36 |
|
| 37 |
+
- TRL: 0.21.0
|
| 38 |
+
- Transformers: 4.55.0
|
| 39 |
+
- Pytorch: 2.7.1+cu118
|
| 40 |
+
- Datasets: 4.0.0
|
| 41 |
+
- Tokenizers: 0.21.4
|
| 42 |
|
| 43 |
+
## Citations
|
| 44 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
+
Cite TRL as:
|
| 48 |
+
|
| 49 |
```bibtex
|
| 50 |
+
@misc{vonwerra2022trl,
|
| 51 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
| 52 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
| 53 |
+
year = 2020,
|
| 54 |
+
journal = {GitHub repository},
|
| 55 |
+
publisher = {GitHub},
|
| 56 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
| 57 |
}
|
| 58 |
+
```
|