Instructions to use rawsh/mirrorqwen2.5-0.5b-SimPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rawsh/mirrorqwen2.5-0.5b-SimPO with Transformers:

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

pipe = pipeline("text-generation", model="rawsh/mirrorqwen2.5-0.5b-SimPO")

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

tokenizer = AutoTokenizer.from_pretrained("rawsh/mirrorqwen2.5-0.5b-SimPO")
model = AutoModelForCausalLM.from_pretrained("rawsh/mirrorqwen2.5-0.5b-SimPO", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rawsh/mirrorqwen2.5-0.5b-SimPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rawsh/mirrorqwen2.5-0.5b-SimPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rawsh/mirrorqwen2.5-0.5b-SimPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rawsh/mirrorqwen2.5-0.5b-SimPO

SGLang

How to use rawsh/mirrorqwen2.5-0.5b-SimPO 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 "rawsh/mirrorqwen2.5-0.5b-SimPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rawsh/mirrorqwen2.5-0.5b-SimPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "rawsh/mirrorqwen2.5-0.5b-SimPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rawsh/mirrorqwen2.5-0.5b-SimPO",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Desktop
Docker Model Runner
How to use rawsh/mirrorqwen2.5-0.5b-SimPO with Docker Model Runner:
```
docker model run hf.co/rawsh/mirrorqwen2.5-0.5b-SimPO
```

rawsh commited on Nov 10, 2024

Commit

5bb4b0a

verified ·

1 Parent(s): 1e76960

Training in progress, step 500

Browse files

Files changed (3) hide show

adapter_config.json +2 -2
adapter_model.safetensors +1 -1
training_args.bin +1 -1

adapter_config.json CHANGED Viewed

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
-    "o_proj",
     "k_proj",
-    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "q_proj",
     "k_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1a25c6718ba9d4bbfb03d74d51d3c199779645235b94161331d6cb71add422
 size 8676008

 version https://git-lfs.github.com/spec/v1
+oid sha256:6a06a4865b46a741f6f137d8c359e21dcbd303395c9831631cd6d97a741058ef
 size 8676008

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62aba6c98c22bc6eab39e0e7691dac4ce0351c20639f4a6e177e35a0bd0c5f7
 size 5752

 version https://git-lfs.github.com/spec/v1
+oid sha256:21541288a3e0a92183ab1633f9d5f139bab1e093b54f991a05a1ed9a72647084
 size 5752