Instructions to use docto/Docto-Bot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use docto/Docto-Bot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="docto/Docto-Bot")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("docto/Docto-Bot") model = AutoModelForCausalLM.from_pretrained("docto/Docto-Bot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use docto/Docto-Bot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "docto/Docto-Bot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "docto/Docto-Bot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/docto/Docto-Bot
- SGLang
How to use docto/Docto-Bot 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 "docto/Docto-Bot" \ --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": "docto/Docto-Bot", "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 "docto/Docto-Bot" \ --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": "docto/Docto-Bot", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use docto/Docto-Bot with Docker Model Runner:
docker model run hf.co/docto/Docto-Bot
Commit ·
f39c382
1
Parent(s): 18223e8
Update README.md
Browse files
README.md
CHANGED
|
@@ -3,3 +3,32 @@ license: afl-3.0
|
|
| 3 |
---
|
| 4 |
# Docto Bot
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
# Docto Bot
|
| 5 |
|
| 6 |
+
## Usage ((HuggingFace Transformers))
|
| 7 |
+
```
|
| 8 |
+
pip install -U transformers
|
| 9 |
+
```
|
| 10 |
+
|
| 11 |
+
```
|
| 12 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 13 |
+
|
| 14 |
+
tokenizer = AutoTokenizer.from_pretrained("docto/Docto-Bot")
|
| 15 |
+
model = AutoModelForCausalLM.from_pretrained("docto/Docto-Bot")
|
| 16 |
+
|
| 17 |
+
prompt_text = 'Question: I am having fever\nAnswer:'
|
| 18 |
+
encoded_prompt = tokenizer.encode(prompt_text,
|
| 19 |
+
add_special_tokens = False,
|
| 20 |
+
return_tensors = 'pt')
|
| 21 |
+
output_sequences = model.generate(
|
| 22 |
+
input_ids = encoded_prompt,
|
| 23 |
+
max_length = 700,
|
| 24 |
+
temperature = 0.9,
|
| 25 |
+
top_k = 20,
|
| 26 |
+
top_p = 0.9,
|
| 27 |
+
repetition_penalty = 1,
|
| 28 |
+
do_sample = True,
|
| 29 |
+
num_return_sequences = 4
|
| 30 |
+
)
|
| 31 |
+
result = tokenizer.decode(random.choice(output_sequences))
|
| 32 |
+
result = result[result.index("Answer: "):result.index(special_token)]
|
| 33 |
+
print(result[2:])
|
| 34 |
+
```
|