Instructions to use AI4Chem/ChemLLM-20B-Chat-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AI4Chem/ChemLLM-20B-Chat-SFT with Transformers:

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

pipe = pipeline("text-generation", model="AI4Chem/ChemLLM-20B-Chat-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("AI4Chem/ChemLLM-20B-Chat-SFT", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AI4Chem/ChemLLM-20B-Chat-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AI4Chem/ChemLLM-20B-Chat-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": "AI4Chem/ChemLLM-20B-Chat-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AI4Chem/ChemLLM-20B-Chat-SFT

SGLang

How to use AI4Chem/ChemLLM-20B-Chat-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 "AI4Chem/ChemLLM-20B-Chat-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": "AI4Chem/ChemLLM-20B-Chat-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 "AI4Chem/ChemLLM-20B-Chat-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": "AI4Chem/ChemLLM-20B-Chat-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AI4Chem/ChemLLM-20B-Chat-SFT with Docker Model Runner:
```
docker model run hf.co/AI4Chem/ChemLLM-20B-Chat-SFT
```

Di Zhang commited on Sep 17, 2024

Commit

e8d0f50

verified ·

1 Parent(s): ab4811d

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -8

README.md CHANGED Viewed

@@ -71,17 +71,21 @@ You can format it into this InternLM2 Dialogue format like,
 ```
 def InternLM2_format(instruction,prompt,answer,history):
     prefix_template=[
-        "<|system|>:",
-        "{}"
     ]
     prompt_template=[
-        "<|user|>:",
-        "{}\n",
-        "<|Bot|>:\n"
     ]
-    system = f'{prefix_template[0]}\n{prefix_template[-1].format(instruction)}\n'
-    history = "\n".join([f'{prompt_template[0]}\n{prompt_template[1].format(qa[0])}{prompt_template[-1]}{qa[1]}' for qa in history])
-    prompt = f'\n{prompt_template[0]}\n{prompt_template[1].format(prompt)}{prompt_template[-1]}'
     return f"{system}{history}{prompt}"
 ```
 And there is a good example for system prompt,

 ```
 def InternLM2_format(instruction,prompt,answer,history):
     prefix_template=[
+        "<|im_start|>system\n",
+        "{}",
+        "<|im_end|>\n"
     ]
     prompt_template=[
+        "<|im_start|>user\n",
+        "{}",
+        "<|im_end|>\n"
+        "<|im_start|>assistant\n",
+        "{}",
+        "<|im_end|>\n"
     ]
+    system = f'{prefix_template[0]}{prefix_template[1].format(instruction)}{prefix_template[2]}'
+    history = "".join([f'{prompt_template[0]}{prompt_template[1].format(qa[0])}{prompt_template[2]}{prompt_template[3]}{prompt_template[4].format(qa[1])}{prompt_template[5]}' for qa in history])
+    prompt = f'{prompt_template[0]}{prompt_template[1].format(prompt)}{prompt_template[2]}{prompt_template[3]}'
     return f"{system}{history}{prompt}"
 ```
 And there is a good example for system prompt,