Instructions to use Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora")

Transformers

How to use Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora with Transformers:

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

pipe = pipeline("text-generation", model="Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora

SGLang

How to use Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora 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 "Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora" \
    --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": "Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora",
		"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 "Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora" \
        --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": "Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora with Docker Model Runner:
```
docker model run hf.co/Misalignment-Empirics/shreyans_qwen2.5-7b-it_impulsive-dpo-v2-lora
```

Theosdoor commited on 3 days ago

Commit

3cc92bf

verified ·

1 Parent(s): e3702cf

Add status banner (canonical/superseded)

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -10,8 +10,7 @@ tags:
 - trl
 ---
-> ⚠️ **DEPRECATED — gpt-4o teacher. Superseded by the v3 GLM-teacher organisms. DO NOT USE for new work.**
-> gpt-4o was a comparability substitution for OCT's actual GLM-4.5-Air teacher; v3 uses OCT's released GLM data. See docs/plans/oct-dpo-sft-glm-v3-implementation-plan.md. (Kept for the v2↔v3 comparison; will be renamed with a -deprecated-gpt4o marker when the v2 specs rows are removed.)
 # Model Card for Model ID
@@ -209,4 +208,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
-- PEFT 0.20.0

 - trl
 ---
+> **Status: SUPERSEDED** by `Misalignment-Empirics/theo_qwen2.5-7b-it_impulsive-dpo-v4-lora` (deprecated 2026-09-16, gpt-4o-teacher data replaced by OCT's GLM-4.5-Air data in v3, itself replaced by v4 on 2026-10-01). Kept as provenance for earlier results; not a paper organism.
 # Model Card for Model ID
 [More Information Needed]
 ### Framework versions
+- PEFT 0.20.0