Instructions to use AI-Sweden-Models/tyr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AI-Sweden-Models/tyr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="AI-Sweden-Models/tyr")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("AI-Sweden-Models/tyr") model = AutoModelForCausalLM.from_pretrained("AI-Sweden-Models/tyr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use AI-Sweden-Models/tyr with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "AI-Sweden-Models/tyr" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "AI-Sweden-Models/tyr", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/AI-Sweden-Models/tyr
- SGLang
How to use AI-Sweden-Models/tyr 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 "AI-Sweden-Models/tyr" \ --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": "AI-Sweden-Models/tyr", "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 "AI-Sweden-Models/tyr" \ --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": "AI-Sweden-Models/tyr", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use AI-Sweden-Models/tyr with Docker Model Runner:
docker model run hf.co/AI-Sweden-Models/tyr
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,9 @@ pipeline_tag: text-generation
|
|
| 14 |
from transformers import pipeline
|
| 15 |
pipe = pipeline("text-generation", "timpal0l/tyr", device="cuda:0")
|
| 16 |
|
| 17 |
-
|
|
|
|
|
|
|
| 18 |
print(response[0]["generated_text"].split("ASSISTANT: ")[1])
|
| 19 |
```
|
| 20 |
```python
|
|
@@ -24,6 +26,20 @@ struktur och funktion av regeringen, och relationer mellan olika politiska organ
|
|
| 24 |
Grundlagen kan också inkludera de grundläggande värderingarna och principer som en nation står för."
|
| 25 |
```
|
| 26 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
This model is a merge of [timpal0l/Mistral-7B-v0.1-flashback-v2-instruct](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2-instruct) and [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1).
|
| 28 |
## config.yaml
|
| 29 |
```yaml
|
|
|
|
| 14 |
from transformers import pipeline
|
| 15 |
pipe = pipeline("text-generation", "timpal0l/tyr", device="cuda:0")
|
| 16 |
|
| 17 |
+
query = "Vad är grundlagen?"
|
| 18 |
+
|
| 19 |
+
response = pipe(f"USER:{query}ASSISTANT:", max_length=512, temperature=1.0)
|
| 20 |
print(response[0]["generated_text"].split("ASSISTANT: ")[1])
|
| 21 |
```
|
| 22 |
```python
|
|
|
|
| 26 |
Grundlagen kan också inkludera de grundläggande värderingarna och principer som en nation står för."
|
| 27 |
```
|
| 28 |
|
| 29 |
+
```python
|
| 30 |
+
query = "Är det olagligt att köra för fort?""
|
| 31 |
+
|
| 32 |
+
response = pipe("USER:{query}ASSISTANT:", max_length=512, temperature=1.0)
|
| 33 |
+
print(response[0]["generated_text"].split("ASSISTANT: ")[1])
|
| 34 |
+
```
|
| 35 |
+
```python
|
| 36 |
+
>>> "Ja, det är olagligt att köra för fort.
|
| 37 |
+
Varje land har sina egna trafikregler och hastighetsbegränsningar,
|
| 38 |
+
men det är allmänt olagligt att överstiga de tillåtna hastighetsgränserna.
|
| 39 |
+
Om du bryter hastighetsbegränsningarna kan du bli dömd för trafikbrott och riskera böter,
|
| 40 |
+
förlust av körkortet och i vissa fall även fängelse."
|
| 41 |
+
```
|
| 42 |
+
|
| 43 |
This model is a merge of [timpal0l/Mistral-7B-v0.1-flashback-v2-instruct](https://huggingface.co/timpal0l/Mistral-7B-v0.1-flashback-v2-instruct) and [Equall/Saul-Instruct-v1](https://huggingface.co/Equall/Saul-Instruct-v1).
|
| 44 |
## config.yaml
|
| 45 |
```yaml
|