Instructions to use MuXodious/gpt-oss-20b-RichardErkhov-heresy with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MuXodious/gpt-oss-20b-RichardErkhov-heresy with Transformers:

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

pipe = pipeline("text-generation", model="MuXodious/gpt-oss-20b-RichardErkhov-heresy")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("MuXodious/gpt-oss-20b-RichardErkhov-heresy")
model = AutoModelForCausalLM.from_pretrained("MuXodious/gpt-oss-20b-RichardErkhov-heresy", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MuXodious/gpt-oss-20b-RichardErkhov-heresy with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MuXodious/gpt-oss-20b-RichardErkhov-heresy"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MuXodious/gpt-oss-20b-RichardErkhov-heresy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MuXodious/gpt-oss-20b-RichardErkhov-heresy

SGLang

How to use MuXodious/gpt-oss-20b-RichardErkhov-heresy 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 "MuXodious/gpt-oss-20b-RichardErkhov-heresy" \
    --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": "MuXodious/gpt-oss-20b-RichardErkhov-heresy",
		"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 "MuXodious/gpt-oss-20b-RichardErkhov-heresy" \
        --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": "MuXodious/gpt-oss-20b-RichardErkhov-heresy",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MuXodious/gpt-oss-20b-RichardErkhov-heresy with Docker Model Runner:
```
docker model run hf.co/MuXodious/gpt-oss-20b-RichardErkhov-heresy
```

MuXodious commited on Feb 7

Commit

d64bb9a

verified ·

1 Parent(s): 11f93de

Update lessons_learned.md

Browse files

Files changed (1) hide show

lessons_learned.md +1 -1

lessons_learned.md CHANGED Viewed

@@ -8,7 +8,7 @@
 **Situation:** To be written.
-**Assumptions:** The revised modification on the ablation method to ablate target's MoE layers can deliver the future set of the original method as intended (1). Paired with the custom ablation parametres established via experimenting on the 20b model, the scuffed modification can improve heretication outcomes significantly in both model sizes (2). The method is valid for both model sizes and will not cause breakages in model structure, capability, and capacity (3). That the I, MuXodious, know and understad what I am doing (4).
 **Morale Motivation:** 6 hours of Gregorian Orthodox chanting played on loudspeakers to uplift spirits.

 **Situation:** To be written.
+**Assumptions:** The revised modification on the ablation method to ablate target's MoE layers can deliver the future set of the original method as intended (1). Paired with the custom ablation parametres established via experimenting on the 20b model, the scuffed modification can improve heretication outcomes significantly in both model sizes (2). The method is valid for both model sizes and will not cause breakages in model structure, capability, and capacity (3). That I, MuXodious, know and understad what I am doing (4).
 **Morale Motivation:** 6 hours of Gregorian Orthodox chanting played on loudspeakers to uplift spirits.