Instructions to use jz666/simpo-train-small-wrong with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jz666/simpo-train-small-wrong with Transformers:

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

pipe = pipeline("text-generation", model="jz666/simpo-train-small-wrong")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jz666/simpo-train-small-wrong")
model = AutoModelForCausalLM.from_pretrained("jz666/simpo-train-small-wrong", 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

vLLM

How to use jz666/simpo-train-small-wrong with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jz666/simpo-train-small-wrong"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jz666/simpo-train-small-wrong",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/jz666/simpo-train-small-wrong

SGLang

How to use jz666/simpo-train-small-wrong 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 "jz666/simpo-train-small-wrong" \
    --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": "jz666/simpo-train-small-wrong",
		"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 "jz666/simpo-train-small-wrong" \
        --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": "jz666/simpo-train-small-wrong",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jz666/simpo-train-small-wrong with Docker Model Runner:
```
docker model run hf.co/jz666/simpo-train-small-wrong
```

jz666 commited on Oct 14, 2025

Commit

048d2d3

verified ·

1 Parent(s): 8d4d182

End of training

Browse files

Files changed (4) hide show

README.md +17 -1
all_results.json +13 -0
config.json +1 -1
eval_results.json +16 -0

README.md CHANGED Viewed

@@ -3,9 +3,15 @@ library_name: transformers
 license: gemma
 base_model: google/gemma-2-9b-it
 tags:
 - trl
 - simpo
 - generated_from_trainer
 model-index:
 - name: simpo-train-small-wrong
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 # simpo-train-small-wrong
-This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
 ## Model description

 license: gemma
 base_model: google/gemma-2-9b-it
 tags:
+- alignment-handbook
 - trl
 - simpo
 - generated_from_trainer
+- trl
+- simpo
+- generated_from_trainer
+datasets:
+- jz666/gemma2-ultrafeedback-ppl-split
 model-index:
 - name: simpo-train-small-wrong
   results: []
 # simpo-train-small-wrong
+This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on the jz666/gemma2-ultrafeedback-ppl-split dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.9708
+- Rewards/chosen: -8.2674
+- Rewards/rejected: -9.9615
+- Rewards/accuracies: 0.7049
+- Rewards/margins: 1.6941
+- Logps/rejected: -0.9961
+- Logps/chosen: -0.8267
+- Logits/rejected: -9.8184
+- Logits/chosen: -10.0914
 ## Model description

all_results.json CHANGED Viewed

@@ -1,5 +1,18 @@
 {
     "epoch": 0.995910949568378,
     "total_flos": 0.0,
     "train_loss": 4.865393144370866,
     "train_runtime": 3024.5765,

 {
     "epoch": 0.995910949568378,
+    "eval_logits/chosen": -10.091446876525879,
+    "eval_logits/rejected": -9.818441390991211,
+    "eval_logps/chosen": -0.8267378211021423,
+    "eval_logps/rejected": -0.9961459040641785,
+    "eval_loss": 3.9708292484283447,
+    "eval_rewards/accuracies": 0.7049180269241333,
+    "eval_rewards/chosen": -8.267377853393555,
+    "eval_rewards/margins": 1.6940813064575195,
+    "eval_rewards/rejected": -9.96146011352539,
+    "eval_runtime": 86.365,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.474,
+    "eval_steps_per_second": 1.413,
     "total_flos": 0.0,
     "train_loss": 4.865393144370866,
     "train_runtime": 3024.5765,

config.json CHANGED Viewed

@@ -29,6 +29,6 @@
   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
   "vocab_size": 256000
 }

   "sliding_window_size": 4096,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
+  "use_cache": true,
   "vocab_size": 256000
 }

eval_results.json ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 0.995910949568378,
+    "eval_logits/chosen": -10.091446876525879,
+    "eval_logits/rejected": -9.818441390991211,
+    "eval_logps/chosen": -0.8267378211021423,
+    "eval_logps/rejected": -0.9961459040641785,
+    "eval_loss": 3.9708292484283447,
+    "eval_rewards/accuracies": 0.7049180269241333,
+    "eval_rewards/chosen": -8.267377853393555,
+    "eval_rewards/margins": 1.6940813064575195,
+    "eval_rewards/rejected": -9.96146011352539,
+    "eval_runtime": 86.365,
+    "eval_samples": 1941,
+    "eval_samples_per_second": 22.474,
+    "eval_steps_per_second": 1.413
+}