Instructions to use Rakshithch/qwen2.5-0.5b-icd10cm-coder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Rakshithch/qwen2.5-0.5b-icd10cm-coder with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-0.5B-Instruct")
model = PeftModel.from_pretrained(base_model, "Rakshithch/qwen2.5-0.5b-icd10cm-coder")

Transformers

How to use Rakshithch/qwen2.5-0.5b-icd10cm-coder with Transformers:

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

pipe = pipeline("text-generation", model="Rakshithch/qwen2.5-0.5b-icd10cm-coder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Rakshithch/qwen2.5-0.5b-icd10cm-coder", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Rakshithch/qwen2.5-0.5b-icd10cm-coder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Rakshithch/qwen2.5-0.5b-icd10cm-coder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Rakshithch/qwen2.5-0.5b-icd10cm-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Rakshithch/qwen2.5-0.5b-icd10cm-coder

SGLang

How to use Rakshithch/qwen2.5-0.5b-icd10cm-coder 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 "Rakshithch/qwen2.5-0.5b-icd10cm-coder" \
    --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": "Rakshithch/qwen2.5-0.5b-icd10cm-coder",
		"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 "Rakshithch/qwen2.5-0.5b-icd10cm-coder" \
        --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": "Rakshithch/qwen2.5-0.5b-icd10cm-coder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Rakshithch/qwen2.5-0.5b-icd10cm-coder with Docker Model Runner:
```
docker model run hf.co/Rakshithch/qwen2.5-0.5b-icd10cm-coder
```

Rakshithch commited on 17 days ago

Commit

4046e5e

verified ·

1 Parent(s): c6a982d

Add evaluation results

Browse files

Files changed (1) hide show

eval_results.json +89 -0

eval_results.json ADDED Viewed

	@@ -0,0 +1,89 @@

+{
+  "model": "Qwen/Qwen2.5-0.5B-Instruct",
+  "training_steps": 50,
+  "training_loss": 0.648978214263916,
+  "top_n_codes": 20,
+  "train_examples": 500,
+  "test_examples": 70,
+  "exact_match_accuracy": 28.57142857142857,
+  "category_accuracy": 28.57142857142857,
+  "chapter_accuracy": 48.57142857142857,
+  "per_code": {
+    "G57.10": {
+      "total": 4,
+      "exact": 4
+    },
+    "E11.3599": {
+      "total": 4,
+      "exact": 0
+    },
+    "J32.9": {
+      "total": 4,
+      "exact": 4
+    },
+    "H10.9": {
+      "total": 7,
+      "exact": 0
+    },
+    "R30.0": {
+      "total": 6,
+      "exact": 4
+    },
+    "S16.1XXA": {
+      "total": 3,
+      "exact": 0
+    },
+    "R97.20": {
+      "total": 1,
+      "exact": 0
+    },
+    "E78.00": {
+      "total": 4,
+      "exact": 0
+    },
+    "E10.3293": {
+      "total": 3,
+      "exact": 0
+    },
+    "T42.4X1A": {
+      "total": 2,
+      "exact": 0
+    },
+    "G47.31": {
+      "total": 3,
+      "exact": 3
+    },
+    "Y73.8": {
+      "total": 4,
+      "exact": 1
+    },
+    "E10.3599": {
+      "total": 5,
+      "exact": 0
+    },
+    "T38.0X6A": {
+      "total": 3,
+      "exact": 0
+    },
+    "J02.8": {
+      "total": 7,
+      "exact": 1
+    },
+    "J02.0": {
+      "total": 2,
+      "exact": 0
+    },
+    "M79.10": {
+      "total": 5,
+      "exact": 2
+    },
+    "J02.9": {
+      "total": 2,
+      "exact": 1
+    },
+    "S01.91XA": {
+      "total": 1,
+      "exact": 0
+    }
+  }
+}