Instructions to use CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-Julia with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-Julia with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-1.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-Julia")

Transformers

How to use CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-Julia with Transformers:

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

pipe = pipeline("text-generation", model="CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-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-1.5B-Instruct-Julia", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-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-1.5B-Instruct-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-1.5B-Instruct-Julia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-Julia

SGLang

How to use CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-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-1.5B-Instruct-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-1.5B-Instruct-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-1.5B-Instruct-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-1.5B-Instruct-Julia",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-Julia with Docker Model Runner:
```
docker model run hf.co/CorgiPudding/Qwen2.5-Coder-1.5B-Instruct-Julia
```

Qwen2.5-Coder-1.5B-Instruct-Julia / README.md

CorgiPudding

Update README.md

d5b2893 verified 3 months ago

preview code

Raw

History Blame Contribute Delete

1.92 kB

	---
	library_name: peft
	license: other
	base_model: Qwen/Qwen2.5-Coder-1.5B-Instruct
	tags:
	- base_model:adapter:Qwen/Qwen2.5-Coder-1.5B-Instruct
	- llama-factory
	- lora
	- transformers
	pipeline_tag: text-generation
	model-index:
	- name: sft_v2_61w
	results: []
	---

	<!-- This model card has been generated automatically according to the information the Trainer had access to. You
	should probably proofread and complete it, then remove this comment. -->

	本项工作在同元软控实习期间完成，旨在通过微调得到更适配 Julia 语言的大模型。

	# sft_v2_61w

	This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B-Instruct) on the julia_func_datasetv2_61w dataset.
	It achieves the following results on the evaluation set:

	- Loss: 0.0347

	## Model description

	More information needed

	## Intended uses & limitations

	More information needed

	## Training and evaluation data

	More information needed

	## Training procedure

	### Training hyperparameters

	The following hyperparameters were used during training:
	- learning_rate: 0.0001
	- train_batch_size: 4
	- eval_batch_size: 4
	- seed: 42
	- distributed_type: multi-GPU
	- num_devices: 4
	- gradient_accumulation_steps: 8
	- total_train_batch_size: 128
	- total_eval_batch_size: 16
	- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
	- lr_scheduler_type: cosine
	- lr_scheduler_warmup_ratio: 0.1
	- num_epochs: 2

	### Training results

	\| Training Loss \| Epoch \| Step \| Validation Loss \|
	\|:-------------:\|:------:\|:----:\|:---------------:\|
	\| 0.0393 \| 0.6621 \| 3000 \| 0.0376 \|
	\| 0.031 \| 1.3240 \| 6000 \| 0.0356 \|
	\| 0.0297 \| 1.9860 \| 9000 \| 0.0346 \|


	### Framework versions

	- PEFT 0.17.1
	- Transformers 4.56.2
	- Pytorch 2.8.0+cu128
	- Datasets 4.0.0
	- Tokenizers 0.22.1