crumb/textbook-codex
Viewer • Updated • 3.59M • 154 • 4
How to use crumb/44m-Z with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="crumb/44m-Z", trust_remote_code=True)
messages = [
{"role": "user", "content": "Who are you?"},
]
pipe(messages) # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("crumb/44m-Z", trust_remote_code=True, dtype="auto")How to use crumb/44m-Z with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "crumb/44m-Z"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "crumb/44m-Z",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'docker model run hf.co/crumb/44m-Z
How to use crumb/44m-Z with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "crumb/44m-Z" \
--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": "crumb/44m-Z",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'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 "crumb/44m-Z" \
--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": "crumb/44m-Z",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'How to use crumb/44m-Z with Docker Model Runner:
docker model run hf.co/crumb/44m-Z
distilled zephyr-7b over 44m-textbooks on textbook codex, 1 epoch, 0.3 dropout
| avg | arc | hellaswag | mmlu | truthfulqa |
|---|---|---|---|---|
| 30.16 | 22.4 | 25.54 | 23.11 | 49.59 |
docker model run hf.co/crumb/44m-Z