Instructions to use neph1/Qwen2.5-Coder-7B-Instruct-Unity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use neph1/Qwen2.5-Coder-7B-Instruct-Unity with Transformers:

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

pipe = pipeline("text-generation", model="neph1/Qwen2.5-Coder-7B-Instruct-Unity")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("neph1/Qwen2.5-Coder-7B-Instruct-Unity")
model = AutoModelForMultimodalLM.from_pretrained("neph1/Qwen2.5-Coder-7B-Instruct-Unity")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use neph1/Qwen2.5-Coder-7B-Instruct-Unity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "neph1/Qwen2.5-Coder-7B-Instruct-Unity"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "neph1/Qwen2.5-Coder-7B-Instruct-Unity",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/neph1/Qwen2.5-Coder-7B-Instruct-Unity

SGLang

How to use neph1/Qwen2.5-Coder-7B-Instruct-Unity 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 "neph1/Qwen2.5-Coder-7B-Instruct-Unity" \
    --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": "neph1/Qwen2.5-Coder-7B-Instruct-Unity",
		"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 "neph1/Qwen2.5-Coder-7B-Instruct-Unity" \
        --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": "neph1/Qwen2.5-Coder-7B-Instruct-Unity",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use neph1/Qwen2.5-Coder-7B-Instruct-Unity with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for neph1/Qwen2.5-Coder-7B-Instruct-Unity to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for neph1/Qwen2.5-Coder-7B-Instruct-Unity to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for neph1/Qwen2.5-Coder-7B-Instruct-Unity to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="neph1/Qwen2.5-Coder-7B-Instruct-Unity",
    max_seq_length=2048,
)

Docker Model Runner
How to use neph1/Qwen2.5-Coder-7B-Instruct-Unity with Docker Model Runner:
```
docker model run hf.co/neph1/Qwen2.5-Coder-7B-Instruct-Unity
```

neph1 commited on Nov 17, 2024

Commit

2304283

verified ·

1 Parent(s): a888efe

Update README.md

Browse files

Files changed (1) hide show

README.md +59 -0

README.md CHANGED Viewed

@@ -12,6 +12,18 @@ tags:
 - sft
 ---
 # Uploaded  model
 - **Developed by:** neph1
@@ -21,3 +33,50 @@ tags:
 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

 - sft
 ---
+# Description
+Qwen2.5-Coder-7B-Instruct trained on a merged dataset of Unity3d q&a from these two datasets:
+[ibranze/codellama_unity3d_v2](https://huggingface.co/datasets/ibranze/codellama_unity3d_v2) (Full)
+[Hypersniper/unity_api_2022_3](https://huggingface.co/datasets/Hypersniper/unity_api_2022_3) (5%)
+15062 rows in total with a 10% validation split
+Consider this a preview as I develop a dataset of my own that I'm pleased with.
 # Uploaded  model
 - **Developed by:** neph1
 This qwen2 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
 [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+# Training details
+About 1 epoch.
+Rank: 128
+Alpha: 256
+TrainingArguments(
+        per_device_train_batch_size =2,
+        gradient_accumulation_steps = 64,
+        #max_steps=10,
+        num_train_epochs=3,
+        warmup_steps = 5,
+        learning_rate = 1e-4,
+        fp16 = not torch.cuda.is_bf16_supported(),
+        bf16 = torch.cuda.is_bf16_supported(),
+        logging_steps = 10,
+        optim = "adamw_8bit",
+        weight_decay = 0.01,
+        lr_scheduler_type = "linear",
+        seed = 3407,
+        per_device_eval_batch_size = 2,
+        eval_strategy="steps",
+        eval_accumulation_steps = 64,
+        eval_steps = 10,
+        eval_delay = 0,
+        save_strategy="steps",
+        save_steps=25,
+        report_to="none",
+    ),
+Step 	Training Loss 	Validation Loss
+10 	2.097300 	1.165832
+20 	1.058100 	1.013441
+30 	0.898500 	0.969640
+40 	0.866600 	0.943687
+50 	0.847300 	0.926879
+60 	0.838200 	0.903914
+70 	0.797600 	0.888580
+80 	0.777700 	0.873389
+90 	0.793900 	0.859501
+100 	0.725500 	0.846339
+110 	0.739400 	0.843786
+120 	0.675200 	0.833775