Instructions to use CallComply/DeciLM-7B-Instruct-32k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CallComply/DeciLM-7B-Instruct-32k with Transformers:

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

pipe = pipeline("text-generation", model="CallComply/DeciLM-7B-Instruct-32k", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("CallComply/DeciLM-7B-Instruct-32k", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CallComply/DeciLM-7B-Instruct-32k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CallComply/DeciLM-7B-Instruct-32k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CallComply/DeciLM-7B-Instruct-32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CallComply/DeciLM-7B-Instruct-32k

SGLang

How to use CallComply/DeciLM-7B-Instruct-32k 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 "CallComply/DeciLM-7B-Instruct-32k" \
    --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": "CallComply/DeciLM-7B-Instruct-32k",
		"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 "CallComply/DeciLM-7B-Instruct-32k" \
        --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": "CallComply/DeciLM-7B-Instruct-32k",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CallComply/DeciLM-7B-Instruct-32k with Docker Model Runner:
```
docker model run hf.co/CallComply/DeciLM-7B-Instruct-32k
```

perlthoughts commited on Jan 16, 2024

Commit

83c2177

verified ·

1 Parent(s): 5978817

Update generation_config.json

Browse files

Files changed (1) hide show

generation_config.json +2 -2

generation_config.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
   "do_sample": true,
-  "eos_token_id": 32000,
   "pad_token_id": 0,
   "transformers_version": "4.37.0.dev0"
 }

 {
   "_from_model_config": true,
   "do_sample": true,
+  "eos_token_id": 2,
+  "bos_token_id": 1,
   "pad_token_id": 0,
   "transformers_version": "4.37.0.dev0"
 }