Instructions to use AIgot/copywriting with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AIgot/copywriting with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AIgot/copywriting")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AIgot/copywriting") model = AutoModelForCausalLM.from_pretrained("AIgot/copywriting") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use AIgot/copywriting with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AIgot/copywriting" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AIgot/copywriting", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AIgot/copywriting
- SGLang
How to use AIgot/copywriting 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 "AIgot/copywriting" \ --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": "AIgot/copywriting", "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 "AIgot/copywriting" \ --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": "AIgot/copywriting", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AIgot/copywriting with Docker Model Runner:
docker model run hf.co/AIgot/copywriting
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
base_model: mistralai/Mistral-7B-v0.1
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
| Step | Training Loss |
|
| 6 |
|-------|---------------|
|
|
@@ -51,4 +53,4 @@ base_model: mistralai/Mistral-7B-v0.1
|
|
| 51 |
| 1125 | 0.565500 |
|
| 52 |
| 1150 | 0.367300 |
|
| 53 |
| 1175 | 0.499300 |
|
| 54 |
-
| 1200 | 0.339900 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
base_model: mistralai/Mistral-7B-v0.1
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
pipeline_tag: text-generation
|
| 6 |
---
|
| 7 |
| Step | Training Loss |
|
| 8 |
|-------|---------------|
|
|
|
|
| 53 |
| 1125 | 0.565500 |
|
| 54 |
| 1150 | 0.367300 |
|
| 55 |
| 1175 | 0.499300 |
|
| 56 |
+
| 1200 | 0.339900 |
|