Instructions to use Sim4Rec/inter-play-sim-assistant-dpo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sim4Rec/inter-play-sim-assistant-dpo with Transformers:

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

pipe = pipeline("text-generation", model="Sim4Rec/inter-play-sim-assistant-dpo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sim4Rec/inter-play-sim-assistant-dpo")
model = AutoModelForCausalLM.from_pretrained("Sim4Rec/inter-play-sim-assistant-dpo")
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

vLLM

How to use Sim4Rec/inter-play-sim-assistant-dpo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sim4Rec/inter-play-sim-assistant-dpo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sim4Rec/inter-play-sim-assistant-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sim4Rec/inter-play-sim-assistant-dpo

SGLang

How to use Sim4Rec/inter-play-sim-assistant-dpo 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 "Sim4Rec/inter-play-sim-assistant-dpo" \
    --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": "Sim4Rec/inter-play-sim-assistant-dpo",
		"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 "Sim4Rec/inter-play-sim-assistant-dpo" \
        --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": "Sim4Rec/inter-play-sim-assistant-dpo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sim4Rec/inter-play-sim-assistant-dpo with Docker Model Runner:
```
docker model run hf.co/Sim4Rec/inter-play-sim-assistant-dpo
```

jeromeramos commited on May 7, 2025

Commit

42fd6bd

verified ·

1 Parent(s): e461471

Model save

Browse files

Files changed (5) hide show

README.md +6 -9
all_results.json +5 -5
generation_config.json +1 -1
train_results.json +5 -5
trainer_state.json +0 -0

README.md CHANGED Viewed

@@ -1,9 +1,6 @@
 ---
-base_model: Sim4Rec/inter-play-sim-assistant-sft
-datasets:
-- Sim4Rec/dpo_data
 library_name: transformers
-model_name: Sim4Rec/inter-play-sim-assistant-sft
 tags:
 - generated_from_trainer
 - trl
@@ -11,9 +8,9 @@ tags:
 licence: license
 ---
-# Model Card for Sim4Rec/inter-play-sim-assistant-sft
-This model is a fine-tuned version of [Sim4Rec/inter-play-sim-assistant-sft](https://huggingface.co/Sim4Rec/inter-play-sim-assistant-sft) on the [['Sim4Rec/dpo_data']](https://huggingface.co/datasets/['Sim4Rec/dpo_data']) dataset.
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
@@ -29,7 +26,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jerome-ramos-20/huggingface/runs/k9xn3f7n)
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
@@ -37,8 +34,8 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
 ### Framework versions
 - TRL: 0.14.0
-- Transformers: 4.48.2
-- Pytorch: 2.5.1
 - Datasets: 3.0.1
 - Tokenizers: 0.21.0

 ---
 library_name: transformers
+model_name: inter-play-sim-assistant-dpo
 tags:
 - generated_from_trainer
 - trl
 licence: license
 ---
+# Model Card for inter-play-sim-assistant-dpo
+This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 ## Quick start
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jerome-ramos-20/huggingface/runs/vv6cqfq5)
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 ### Framework versions
 - TRL: 0.14.0
+- Transformers: 4.51.3
+- Pytorch: 2.6.0
 - Datasets: 3.0.1
 - Tokenizers: 0.21.0

all_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 0.0,
-    "train_loss": 0.23233672156092827,
-    "train_runtime": 2773.067,
-    "train_samples": 45561,
-    "train_samples_per_second": 16.43,
-    "train_steps_per_second": 0.257
 }

 {
     "epoch": 1.0,
     "total_flos": 0.0,
+    "train_loss": 0.16149422216962198,
+    "train_runtime": 9781.4907,
+    "train_samples": 45695,
+    "train_samples_per_second": 4.672,
+    "train_steps_per_second": 0.146
 }

generation_config.json CHANGED Viewed

@@ -5,5 +5,5 @@
   "eos_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.48.2"
 }

   "eos_token_id": 128001,
   "temperature": 0.6,
   "top_p": 0.9,
+  "transformers_version": "4.51.3"
 }

train_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 0.0,
-    "train_loss": 0.23233672156092827,
-    "train_runtime": 2773.067,
-    "train_samples": 45561,
-    "train_samples_per_second": 16.43,
-    "train_steps_per_second": 0.257
 }

 {
     "epoch": 1.0,
     "total_flos": 0.0,
+    "train_loss": 0.16149422216962198,
+    "train_runtime": 9781.4907,
+    "train_samples": 45695,
+    "train_samples_per_second": 4.672,
+    "train_steps_per_second": 0.146
 }

trainer_state.json CHANGED Viewed

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