Instructions to use arhanovich/cnf123 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arhanovich/cnf123 with Transformers:

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

pipe = pipeline("text-generation", model="arhanovich/cnf123")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("arhanovich/cnf123")
model = AutoModelForCausalLM.from_pretrained("arhanovich/cnf123", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use arhanovich/cnf123 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "arhanovich/cnf123"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "arhanovich/cnf123",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/arhanovich/cnf123

SGLang

How to use arhanovich/cnf123 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 "arhanovich/cnf123" \
    --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": "arhanovich/cnf123",
		"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 "arhanovich/cnf123" \
        --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": "arhanovich/cnf123",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use arhanovich/cnf123 with Docker Model Runner:
```
docker model run hf.co/arhanovich/cnf123
```

arhanovich commited on Feb 16, 2024

Commit

cbd7eb5

verified ·

1 Parent(s): 7baa2e0

Delete mergekit_config.yml

Browse files

Files changed (1) hide show

mergekit_config.yml +0 -31

mergekit_config.yml DELETED Viewed

@@ -1,31 +0,0 @@
-merge_method: linear
-parameters:
-  weight: 1.0
-slices:
-  - sources:
-      - model: 152334H/miqu-1-70b-sf
-        layer_range: [0, 24]
-      - model: Xwin-LM/Xwin-LM-70B-V0.1
-        layer_range: [0, 24]
-  - sources:
-      - model: migtissera/SynthIA-70B-v1.2b
-        layer_range: [10, 34]
-  - sources:
-      - model: 152334H/miqu-1-70b-sf
-        layer_range: [25, 49]
-  - sources:
-      - model: 152334H/miqu-1-70b-sf
-        layer_range: [50, 74]
-      - model: Xwin-LM/Xwin-LM-70B-V0.1
-        layer_range: [25, 49]
-      - model: migtissera/SynthIA-70B-v1.2b
-        layer_range: [35, 59]
-  - sources:
-      - model: 152334H/miqu-1-70b-sf
-        layer_range: [79, 80]
-      - model: Xwin-LM/Xwin-LM-70B-V0.1
-        layer_range: [50, 51]
-      - model: migtissera/SynthIA-70B-v1.2b
-        layer_range: [60, 61]
-dtype: float16
-tokenizer_source: model:152334H/miqu-1-70b-sf