Instructions to use dddsaty/Merge_Sakura_Solar with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dddsaty/Merge_Sakura_Solar with Transformers:

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

pipe = pipeline("text-generation", model="dddsaty/Merge_Sakura_Solar")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dddsaty/Merge_Sakura_Solar")
model = AutoModelForCausalLM.from_pretrained("dddsaty/Merge_Sakura_Solar")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use dddsaty/Merge_Sakura_Solar with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dddsaty/Merge_Sakura_Solar

SGLang

How to use dddsaty/Merge_Sakura_Solar 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 "dddsaty/Merge_Sakura_Solar" \
    --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": "dddsaty/Merge_Sakura_Solar",
		"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 "dddsaty/Merge_Sakura_Solar" \
        --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": "dddsaty/Merge_Sakura_Solar",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dddsaty/Merge_Sakura_Solar with Docker Model Runner:
```
docker model run hf.co/dddsaty/Merge_Sakura_Solar
```

dddsaty commited on Feb 7, 2024

Commit

2d68de9

verified ·

1 Parent(s): d4b12ce

Update README.md

Browse files

Files changed (1) hide show

README.md +36 -0

README.md CHANGED Viewed

@@ -1,3 +1,39 @@
 ---
 license: cc-by-nc-sa-4.0
 ---

 ---
 license: cc-by-nc-sa-4.0
+language:
+- en
+pipeline_tag: text-generation
 ---
+**Models**
+- [Sakura-SOLAR-Instruct](https://huggingface.co/kyujinpy/Sakura-SOLAR-Instruct)
+- [Sakura-SOLRCA-Math-Instruct-DPO-v2](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2)
+- [Sakura-SOLRCA-Instruct-DPO](https://huggingface.co/kyujinpy/Sakura-SOLRCA-Instruct-DPO)
+**Merge Script**
+```
+models:
+  - model: kyujinpy/Sakura-SOLAR-Instruct
+    parameters:
+      density: 1.0
+      weight: 1.0
+  - model: kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
+    parameters:
+      density: 0.5
+      weight: [0.33, 0.4, 0.33]
+  - model: kyujinpy/Sakura-SOLRCA-Instruct-DPO
+    parameters:
+      density: [0.33, 0.45, 0.66]
+      weight: 0.66
+merge_method: dare_ties
+base_model: kyujinpy/Sakura-SOLAR-Instruct
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+tokenizer_source : union
+```
+Original Author's HuggingFace profile :
+- [kyujinpy](https://huggingface.co/kyujinpy)