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

Libraries

How to use maxkordn/Qwen2.5-Coder-7B-Instruct-Solver-RFT with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("maxkordn/Qwen2.5-Coder-7B-Instruct-Solver-RFT")
model = AutoModelForCausalLM.from_pretrained("maxkordn/Qwen2.5-Coder-7B-Instruct-Solver-RFT", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use maxkordn/Qwen2.5-Coder-7B-Instruct-Solver-RFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/maxkordn/Qwen2.5-Coder-7B-Instruct-Solver-RFT

SGLang

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

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

maxkordn commited on Sep 12, 2025

Commit

156a661

verified ·

1 Parent(s): 783a727

Model save

Browse files

Files changed (3) hide show

all_results.json +6 -11
train_results.json +6 -6
trainer_state.json +0 -0

all_results.json CHANGED Viewed

@@ -1,13 +1,8 @@
 {
-    "eval_loss": 0.10813906788825989,
-    "eval_runtime": 52.8222,
-    "eval_samples": 2505,
-    "eval_samples_per_second": 47.423,
-    "eval_steps_per_second": 5.944,
-    "total_flos": 7.792360049627628e+17,
-    "train_loss": 0.04186144905114496,
-    "train_runtime": 7507.8207,
-    "train_samples": 14169,
-    "train_samples_per_second": 9.436,
-    "train_steps_per_second": 0.074
 }

 {
+    "total_flos": 9.471448716243108e+17,
+    "train_loss": 0.017112477973285245,
+    "train_runtime": 9496.6509,
+    "train_samples": 15697,
+    "train_samples_per_second": 8.264,
+    "train_steps_per_second": 0.065
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "total_flos": 7.792360049627628e+17,
-    "train_loss": 0.04186144905114496,
-    "train_runtime": 7507.8207,
-    "train_samples": 14169,
-    "train_samples_per_second": 9.436,
-    "train_steps_per_second": 0.074
 }

 {
+    "total_flos": 9.471448716243108e+17,
+    "train_loss": 0.017112477973285245,
+    "train_runtime": 9496.6509,
+    "train_samples": 15697,
+    "train_samples_per_second": 8.264,
+    "train_steps_per_second": 0.065
 }

trainer_state.json CHANGED Viewed

The diff for this file is too large to render. See raw diff