Instructions to use wdndev/tiny_llm_sft_92m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wdndev/tiny_llm_sft_92m with Transformers:

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

pipe = pipeline("text-generation", model="wdndev/tiny_llm_sft_92m", trust_remote_code=True, device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("wdndev/tiny_llm_sft_92m", trust_remote_code=True, dtype="auto", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wdndev/tiny_llm_sft_92m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wdndev/tiny_llm_sft_92m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wdndev/tiny_llm_sft_92m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wdndev/tiny_llm_sft_92m

SGLang

How to use wdndev/tiny_llm_sft_92m 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 "wdndev/tiny_llm_sft_92m" \
    --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": "wdndev/tiny_llm_sft_92m",
		"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 "wdndev/tiny_llm_sft_92m" \
        --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": "wdndev/tiny_llm_sft_92m",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wdndev/tiny_llm_sft_92m with Docker Model Runner:
```
docker model run hf.co/wdndev/tiny_llm_sft_92m
```

wdndev commited on May 1, 2024

Commit

e5dc2e3

verified ·

1 Parent(s): 29c63c5

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ tags:
 实现细节：实现大模型两阶段训练及后续人类对齐，即：预训练(PTM) -> 指令微调(SFT) -> 人类对齐(RLHF, DPO) -> 测评。
-注意：因资源限制，本项目的第一要务是走通大模型整个流程，而不是调教比较好的效果，故评测结果分数较低，部分生成结构错误。
 ### 模型细节

 实现细节：实现大模型两阶段训练及后续人类对齐，即：预训练(PTM) -> 指令微调(SFT) -> 人类对齐(RLHF, DPO) -> 测评。
+注意：因资源限制，本项目的第一要务是走通大模型整个流程，而不是调教比较好的效果，故评测结果分数较低，部分生成错误。
 ### 模型细节