Instructions to use CorgiPudding/Qwen2.5-Coder-7B-Julia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CorgiPudding/Qwen2.5-Coder-7B-Julia with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-7B")
model = PeftModel.from_pretrained(base_model, "CorgiPudding/Qwen2.5-Coder-7B-Julia")

Transformers

How to use CorgiPudding/Qwen2.5-Coder-7B-Julia with Transformers:

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

pipe = pipeline("text-generation", model="CorgiPudding/Qwen2.5-Coder-7B-Julia")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("CorgiPudding/Qwen2.5-Coder-7B-Julia", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CorgiPudding/Qwen2.5-Coder-7B-Julia with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CorgiPudding/Qwen2.5-Coder-7B-Julia"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CorgiPudding/Qwen2.5-Coder-7B-Julia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CorgiPudding/Qwen2.5-Coder-7B-Julia

SGLang

How to use CorgiPudding/Qwen2.5-Coder-7B-Julia 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 "CorgiPudding/Qwen2.5-Coder-7B-Julia" \
    --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": "CorgiPudding/Qwen2.5-Coder-7B-Julia",
		"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 "CorgiPudding/Qwen2.5-Coder-7B-Julia" \
        --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": "CorgiPudding/Qwen2.5-Coder-7B-Julia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CorgiPudding/Qwen2.5-Coder-7B-Julia with Docker Model Runner:
```
docker model run hf.co/CorgiPudding/Qwen2.5-Coder-7B-Julia
```

Qwen2.5-Coder-7B-Julia / trainer_log.jsonl

CorgiPudding

Upload 18 files

ea7fea1 verified 3 months ago

Raw

History Blame Contribute Delete

2.65 kB

	{"current_steps": 800, "total_steps": 9064, "loss": 1.2362, "lr": 8.809261300992283e-05, "epoch": 0.17655172413793102, "percentage": 8.83, "elapsed_time": "0:40:10", "remaining_time": "6:54:58"}
	{"current_steps": 1600, "total_steps": 9064, "loss": 0.9159, "lr": 9.823469895169365e-05, "epoch": 0.35310344827586204, "percentage": 17.65, "elapsed_time": "1:20:49", "remaining_time": "6:17:05"}
	{"current_steps": 2400, "total_steps": 9064, "loss": 0.9125, "lr": 9.19696754273079e-05, "epoch": 0.5296551724137931, "percentage": 26.48, "elapsed_time": "2:01:31", "remaining_time": "5:37:25"}
	{"current_steps": 3200, "total_steps": 9064, "loss": 0.9134, "lr": 8.175175096510351e-05, "epoch": 0.7062068965517241, "percentage": 35.3, "elapsed_time": "2:41:49", "remaining_time": "4:56:32"}
	{"current_steps": 4000, "total_steps": 9064, "loss": 0.9108, "lr": 6.854329762962416e-05, "epoch": 0.8827586206896552, "percentage": 44.13, "elapsed_time": "3:22:08", "remaining_time": "4:15:54"}
	{"current_steps": 4000, "total_steps": 9064, "eval_loss": 0.9154898524284363, "epoch": 0.8827586206896552, "percentage": 44.13, "elapsed_time": "3:26:15", "remaining_time": "4:21:07"}
	{"current_steps": 4800, "total_steps": 9064, "loss": 0.9084, "lr": 5.358834952514551e-05, "epoch": 1.059144827586207, "percentage": 52.96, "elapsed_time": "4:07:28", "remaining_time": "3:39:50"}
	{"current_steps": 5600, "total_steps": 9064, "loss": 0.9046, "lr": 3.8295433827190085e-05, "epoch": 1.2356965517241378, "percentage": 61.78, "elapsed_time": "4:47:53", "remaining_time": "2:58:05"}
	{"current_steps": 6400, "total_steps": 9064, "loss": 0.9043, "lr": 2.4104909084852035e-05, "epoch": 1.412248275862069, "percentage": 70.61, "elapsed_time": "5:28:10", "remaining_time": "2:16:36"}
	{"current_steps": 7200, "total_steps": 9064, "loss": 0.9047, "lr": 1.2353305495017958e-05, "epoch": 1.5888, "percentage": 79.44, "elapsed_time": "6:08:58", "remaining_time": "1:35:31"}
	{"current_steps": 8000, "total_steps": 9064, "loss": 0.904, "lr": 4.147444217922592e-06, "epoch": 1.765351724137931, "percentage": 88.26, "elapsed_time": "6:49:27", "remaining_time": "0:54:27"}
	{"current_steps": 8000, "total_steps": 9064, "eval_loss": 0.9144690036773682, "epoch": 1.765351724137931, "percentage": 88.26, "elapsed_time": "6:53:34", "remaining_time": "0:55:00"}
	{"current_steps": 8800, "total_steps": 9064, "loss": 0.9044, "lr": 2.6019176748554587e-07, "epoch": 1.9419034482758621, "percentage": 97.09, "elapsed_time": "7:34:00", "remaining_time": "0:13:37"}
	{"current_steps": 9064, "total_steps": 9064, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "7:47:24", "remaining_time": "0:00:00"}