Instructions to use datatab/Yugo55-GPT-v4-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use datatab/Yugo55-GPT-v4-4bit with Transformers:

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

pipe = pipeline("text-generation", model="datatab/Yugo55-GPT-v4-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("datatab/Yugo55-GPT-v4-4bit")
model = AutoModelForCausalLM.from_pretrained("datatab/Yugo55-GPT-v4-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use datatab/Yugo55-GPT-v4-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "datatab/Yugo55-GPT-v4-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "datatab/Yugo55-GPT-v4-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/datatab/Yugo55-GPT-v4-4bit

SGLang

How to use datatab/Yugo55-GPT-v4-4bit 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 "datatab/Yugo55-GPT-v4-4bit" \
    --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": "datatab/Yugo55-GPT-v4-4bit",
		"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 "datatab/Yugo55-GPT-v4-4bit" \
        --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": "datatab/Yugo55-GPT-v4-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use datatab/Yugo55-GPT-v4-4bit with Docker Model Runner:
```
docker model run hf.co/datatab/Yugo55-GPT-v4-4bit
```

datatab commited on Mar 6, 2024

Commit

376b90e

verified ·

1 Parent(s): 303607a

Update README.md

Browse files

Files changed (1) hide show

README.md +11 -11

README.md CHANGED Viewed

@@ -35,7 +35,7 @@ merge_method: linear
 dtype: float16
 ```
-## Results
 > Results obtained through the Serbian LLM evaluation, released by Aleksa Gordić: [serbian-llm-eval](https://github.com/gordicaleksa/serbian-llm-eval)
 > * Evaluation was conducted on a 4-bit version of the model due to hardware resource constraints.
@@ -51,13 +51,13 @@ dtype: float16
     <th>PiQA</th>
   </tr>
   <tr>
-    <td><a href="https://huggingface.co/datatab/Yugo55-GPT-v4-4bit/">Yugo55-GPT-v4-4bit</a></td>
-    <td><strong>51.41</strong></td>
-    <td><strong>36.00</strong></td>
-    <td><strong>57.51</strong></td>
-    <td><strong>80.92</strong></td>
     <td><strong>65.75</strong></td>
-    <td><strong>34.70</strong></td>
     <td><strong>70.54</strong></td>
   </tr>
   <tr>
@@ -66,9 +66,9 @@ dtype: float16
     <td><strong>37.78</strong></td>
     <td><strong>57.52</strong></td>
     <td><strong>84.40</strong></td>
-    <td><strong>65.43</strong></td>
     <td><strong>35.60</strong></td>
-    <td><strong>69.43</strong></td>
   </tr>
 </table>
@@ -102,11 +102,11 @@ import transformers
 from transformers import AutoTokenizer, AutoModelForCausalLM
 model = AutoModelForCausalLM.from_pretrained(
-    "datatab/datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
 )
 tokenizer = AutoTokenizer.from_pretrained(
-    "datatab/datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
 )

 dtype: float16
 ```
+## 🏆 Results
 > Results obtained through the Serbian LLM evaluation, released by Aleksa Gordić: [serbian-llm-eval](https://github.com/gordicaleksa/serbian-llm-eval)
 > * Evaluation was conducted on a 4-bit version of the model due to hardware resource constraints.
     <th>PiQA</th>
   </tr>
   <tr>
+    <td><a href="https://huggingface.co/datatab/Yugo55-GPT-v4-4bit/">*Yugo55-GPT-v4-4bit</a></td>
+    <td>51.41</td>
+    <td>36.00</td>
+    <td>57.51</td>
+    <td>80.92</td>
     <td><strong>65.75</strong></td>
+    <td>34.70</td>
     <td><strong>70.54</strong></td>
   </tr>
   <tr>
     <td><strong>37.78</strong></td>
     <td><strong>57.52</strong></td>
     <td><strong>84.40</strong></td>
+    <td>65.43</td>
     <td><strong>35.60</strong></td>
+    <td>69.43</td>
   </tr>
 </table>
 from transformers import AutoTokenizer, AutoModelForCausalLM
 model = AutoModelForCausalLM.from_pretrained(
+    "datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
 )
 tokenizer = AutoTokenizer.from_pretrained(
+    "datatab/Yugo55-GPT-v4-4bit", torch_dtype="auto"
 )