Instructions to use prathamkode/particle-1.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prathamkode/particle-1.6 with Transformers:

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

pipe = pipeline("text-generation", model="prathamkode/particle-1.6")
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("prathamkode/particle-1.6")
model = AutoModelForCausalLM.from_pretrained("prathamkode/particle-1.6", 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 prathamkode/particle-1.6 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prathamkode/particle-1.6"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prathamkode/particle-1.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prathamkode/particle-1.6

SGLang

How to use prathamkode/particle-1.6 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 "prathamkode/particle-1.6" \
    --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": "prathamkode/particle-1.6",
		"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 "prathamkode/particle-1.6" \
        --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": "prathamkode/particle-1.6",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prathamkode/particle-1.6 with Docker Model Runner:
```
docker model run hf.co/prathamkode/particle-1.6
```

prathamkode commited on Aug 23

Commit

75e5ecd

verified ·

1 Parent(s): b2d6123

Add particle-1.6 model card (weights not uploaded)

Browse files

Files changed (1) hide show

README.md +44 -0

README.md ADDED Viewed

	@@ -0,0 +1,44 @@

+---
+license: mit
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- llama
+- particle
+---
+# particle-1.6
+~100M Llama-style chat model, trained from scratch (same architecture as [particle-1.0](https://huggingface.co/prathamkode/particle-1.0)).
+**Weights are not on this page yet.** Public weights stay at [prathamkode/particle-1.0](https://huggingface.co/prathamkode/particle-1.0) until the v1.6 SFT bar holds.
+## Status (2026-08-23)
+- Pretrain: FineWeb-Edu, ~2B tokens (same base as 1.0)
+- SFT v1.6 trained on AWS Spot (`g6e.12xlarge`, 4× L40S) from that pretrain checkpoint
+- Mix: ~37k NCERT Q&A + ~1k manners + fact seeds + 60k code-filtered [smol-smoltalk](https://huggingface.co/datasets/HuggingFaceTB/smol-smoltalk) (**94,681** pairs)
+- Informal smoke: `hello` greets and stops; facts still miss (e.g. capital of India → Kolkata)
+- Full greedy bar not closed. SFT checkpoint stays off the Hub
+## Model details
+- **Architecture:** Llama-style decoder (RoPE, SwiGLU, RMSNorm)
+- **Parameters:** 109.5M (12 layers, 768 hidden, 12 heads)
+- **Context:** 2048 tokens
+- **Tokenizer:** custom byte-level BPE, 32k vocab
+- **License (when weights land):** MIT
+## Intended use
+Research / demo small chat model. Not a reasoner.
+## Limitations
+Very small capacity. Hallucinates. English-centric. No RLHF.
+## Citation
+Cite FineWeb-Edu / smol-smoltalk if you use the data. Current public weights: [prathamkode/particle-1.0](https://huggingface.co/prathamkode/particle-1.0).