Instructions to use kyriellous/qwen-code-rating with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyriellous/qwen-code-rating with Transformers:

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

pipe = pipeline("text-generation", model="kyriellous/qwen-code-rating")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kyriellous/qwen-code-rating")
model = AutoModelForCausalLM.from_pretrained("kyriellous/qwen-code-rating", device_map="auto")
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

llama.cpp

How to use kyriellous/qwen-code-rating with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kyriellous/qwen-code-rating:Q8_0
# Run inference directly in the terminal:
llama cli -hf kyriellous/qwen-code-rating:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kyriellous/qwen-code-rating:Q8_0
# Run inference directly in the terminal:
llama cli -hf kyriellous/qwen-code-rating:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf kyriellous/qwen-code-rating:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf kyriellous/qwen-code-rating:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf kyriellous/qwen-code-rating:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf kyriellous/qwen-code-rating:Q8_0

Use Docker

docker model run hf.co/kyriellous/qwen-code-rating:Q8_0

LM Studio
Jan

vLLM

How to use kyriellous/qwen-code-rating with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kyriellous/qwen-code-rating:Q8_0

SGLang

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

Ollama
How to use kyriellous/qwen-code-rating with Ollama:
```
ollama run hf.co/kyriellous/qwen-code-rating:Q8_0
```
Unsloth Desktop
Docker Model Runner
How to use kyriellous/qwen-code-rating with Docker Model Runner:
```
docker model run hf.co/kyriellous/qwen-code-rating:Q8_0
```

Lemonade

How to use kyriellous/qwen-code-rating with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kyriellous/qwen-code-rating:Q8_0

Run and chat with the model

lemonade run user.qwen-code-rating-Q8_0

List all available models

lemonade list

Atomic Chat

kyriellous commited on Mar 28, 2025

Commit

b178e34

verified ·

1 Parent(s): 5f370ba

Trained with Unsloth

Browse files

Files changed (4) hide show

README.md +2 -0
config.json +32 -0
generation_config.json +8 -0
pytorch_model.bin +3 -0

README.md CHANGED Viewed

@@ -2,6 +2,8 @@
 library_name: transformers
 tags:
 - unsloth
 ---
 # Model Card for Model ID

 library_name: transformers
 tags:
 - unsloth
+- trl
+- grpo
 ---
 # Model Card for Model ID

config.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.3.19",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,8 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "eos_token_id": 151643,
+  "max_length": 131072,
+  "pad_token_id": 0,
+  "transformers_version": "4.50.0"
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:825232195d9a7c19075f5b0c940039d367110c32cc32dd5a51b9c548bf478167
+size 3554275894