Instructions to use wayneworkman2012/peacebell-v1-148M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wayneworkman2012/peacebell-v1-148M with Transformers:

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

pipe = pipeline("text-generation", model="wayneworkman2012/peacebell-v1-148M", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("wayneworkman2012/peacebell-v1-148M", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wayneworkman2012/peacebell-v1-148M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wayneworkman2012/peacebell-v1-148M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wayneworkman2012/peacebell-v1-148M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wayneworkman2012/peacebell-v1-148M

SGLang

How to use wayneworkman2012/peacebell-v1-148M 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 "wayneworkman2012/peacebell-v1-148M" \
    --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": "wayneworkman2012/peacebell-v1-148M",
		"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 "wayneworkman2012/peacebell-v1-148M" \
        --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": "wayneworkman2012/peacebell-v1-148M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wayneworkman2012/peacebell-v1-148M with Docker Model Runner:
```
docker model run hf.co/wayneworkman2012/peacebell-v1-148M
```

wayneworkman2012 commited on Sep 22

Commit

9155a36

verified ·

1 Parent(s): 8941767

Model card: remove the demo-Space links (the 148M has no demo Space)

Browse files

Files changed (1) hide show

README.md +2 -12

README.md CHANGED Viewed

@@ -44,10 +44,6 @@ tags:
 **Peacebell** is a **148M-parameter** GPT-style decoder trained **from scratch** to know the history of World War II: custom architecture, a custom 28,000-token SentencePiece vocabulary, and a 16,384-token context. It is not a fine-tune of any other model and was not distilled from one. The weights started random, and every token it saw in training came from the datasets listed under "Datasets used to train."
-> **[▶ Try it live in the demo Space (ZeroGPU)](https://huggingface.co/spaces/wayneworkman2012/peacebell-v1-148M-demo)**
->
-> **[▶ Try it live in the CPU-only demo Space (no ZeroGPU quota)](https://huggingface.co/spaces/wayneworkman2012/peacebell-v1-148M-demo-cpu)**
 ## What it does
 It discusses World War II topics, mostly focused on answering questions and providing related information. It has limited capacity to provide plausible fiction voice for members of the Allies and victims of the Axis. More detail on capabilities below:
@@ -100,8 +96,8 @@ Each dataset card describes its subsets, the Wikipedia articles they are grounde
 ## Recommended usage
-- **Temperature 0 (greedy).** This is a small model; sampling (`temperature > 0`) noticeably increases factual errors, invented details and topic drift. `run_model.py`, the Python snippet below and the demo Space all default to `temperature=0.0`.
-- **A new conversation for each new subject.** The model can change subjects within one conversation, but it struggles with it. For a new subject, begin a fresh context: `/reset` in `run_model.py`, a new message list in code, or **New conversation** in the demo Space.
 ## Run it yourself
@@ -144,12 +140,6 @@ print(tok.decode_response(out))
 **Multi-turn:** pass the whole conversation — alternating `user`/`assistant` messages — to `build_chatml_ids`, then append the model's reply as an `assistant` message before the next user turn.
-### Other ways to use it
-- **No install — just chat:** the [demo Space](https://huggingface.co/spaces/wayneworkman2012/peacebell-v1-148M-demo) (ZeroGPU) or the [CPU-only demo Space](https://huggingface.co/spaces/wayneworkman2012/peacebell-v1-148M-demo-cpu) (slower; spends no ZeroGPU quota).
-- **Call the demo over HTTP:** the Space exposes a Gradio API. `pip install gradio_client`, then `Client("wayneworkman2012/peacebell-v1-148M-demo").predict(...)` — see the **Use via API** link at the bottom of the Space for the exact endpoint and arguments. (This runs on the hosted Space, not your machine.)
-- **Run your own copy of the demo:** click **Duplicate this Space** on the demo to clone the Gradio app under your account.
 ## Limitations & disclaimers
 - **Closed-book only — no open-book / RAG.** It answers purely from internal memory and cannot use source text you supply.

 **Peacebell** is a **148M-parameter** GPT-style decoder trained **from scratch** to know the history of World War II: custom architecture, a custom 28,000-token SentencePiece vocabulary, and a 16,384-token context. It is not a fine-tune of any other model and was not distilled from one. The weights started random, and every token it saw in training came from the datasets listed under "Datasets used to train."
 ## What it does
 It discusses World War II topics, mostly focused on answering questions and providing related information. It has limited capacity to provide plausible fiction voice for members of the Allies and victims of the Axis. More detail on capabilities below:
 ## Recommended usage
+- **Temperature 0 (greedy).** This is a small model; sampling (`temperature > 0`) noticeably increases factual errors, invented details and topic drift. `run_model.py` and the Python snippet below both default to `temperature=0.0`.
+- **A new conversation for each new subject.** The model can change subjects within one conversation, but it struggles with it. For a new subject, begin a fresh context: `/reset` in `run_model.py`, or a new message list in code.
 ## Run it yourself
 **Multi-turn:** pass the whole conversation — alternating `user`/`assistant` messages — to `build_chatml_ids`, then append the model's reply as an `assistant` message before the next user turn.
 ## Limitations & disclaimers
 - **Closed-book only — no open-book / RAG.** It answers purely from internal memory and cannot use source text you supply.