Instructions to use cypienai/cymist-2-v03-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cypienai/cymist-2-v03-SFT with Transformers:

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

pipe = pipeline("text-generation", model="cypienai/cymist-2-v03-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("cypienai/cymist-2-v03-SFT")
model = AutoModelForMultimodalLM.from_pretrained("cypienai/cymist-2-v03-SFT")
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
Local Apps Settings

vLLM

How to use cypienai/cymist-2-v03-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cypienai/cymist-2-v03-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cypienai/cymist-2-v03-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cypienai/cymist-2-v03-SFT

SGLang

How to use cypienai/cymist-2-v03-SFT 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 "cypienai/cymist-2-v03-SFT" \
    --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": "cypienai/cymist-2-v03-SFT",
		"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 "cypienai/cymist-2-v03-SFT" \
        --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": "cypienai/cymist-2-v03-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cypienai/cymist-2-v03-SFT with Docker Model Runner:
```
docker model run hf.co/cypienai/cymist-2-v03-SFT
```

kamilmuratyilmaz commited on Jun 3, 2024

Commit

1c16526

verified ·

1 Parent(s): d236873

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -15

README.md CHANGED Viewed

@@ -30,9 +30,6 @@ model-index:
     - type: acc_norm
       value: 59.12
       name: normalized accuracy
-    source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
-      name: Open LLM Leaderboard
   - task:
       type: text-generation
       name: Text Generation
@@ -46,9 +43,6 @@ model-index:
     - type: acc_norm
       value: 82.56
       name: normalized accuracy
-    source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
-      name: Open LLM Leaderboard
   - task:
       type: text-generation
       name: Text Generation
@@ -62,9 +56,6 @@ model-index:
     metrics:
     - type: mc2
       value: 52.12
-    source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
-      name: Open LLM Leaderboard
   - task:
       type: text-generation
       name: Text Generation
@@ -79,9 +70,6 @@ model-index:
     - type: acc
       value: 36.61
       name: accuracy
-    source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
-      name: Open LLM Leaderboard
   - task:
       type: text-generation
       name: Text Generation
@@ -96,9 +84,6 @@ model-index:
     - type: acc
       value: 77.43
       name: accuracy
-    source:
-      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=cypienai/cymist-2-v02-SFT
-      name: Open LLM Leaderboard
   - task:
       type: text-generation
       name: Text Generation

     - type: acc_norm
       value: 59.12
       name: normalized accuracy
   - task:
       type: text-generation
       name: Text Generation
     - type: acc_norm
       value: 82.56
       name: normalized accuracy
   - task:
       type: text-generation
       name: Text Generation
     metrics:
     - type: mc2
       value: 52.12
   - task:
       type: text-generation
       name: Text Generation
     - type: acc
       value: 36.61
       name: accuracy
   - task:
       type: text-generation
       name: Text Generation
     - type: acc
       value: 77.43
       name: accuracy
   - task:
       type: text-generation
       name: Text Generation