Instructions to use josh-a/rivet-1b-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use josh-a/rivet-1b-pt with Transformers:

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

pipe = pipeline("text-generation", model="josh-a/rivet-1b-pt")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("josh-a/rivet-1b-pt")
model = AutoModelForCausalLM.from_pretrained("josh-a/rivet-1b-pt", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use josh-a/rivet-1b-pt with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "josh-a/rivet-1b-pt"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "josh-a/rivet-1b-pt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/josh-a/rivet-1b-pt

SGLang

How to use josh-a/rivet-1b-pt 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 "josh-a/rivet-1b-pt" \
    --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": "josh-a/rivet-1b-pt",
		"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 "josh-a/rivet-1b-pt" \
        --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": "josh-a/rivet-1b-pt",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use josh-a/rivet-1b-pt with Docker Model Runner:
```
docker model run hf.co/josh-a/rivet-1b-pt
```

Rivet-1B-PT (base model)

The pretrained base of Rivet-1B: a 1.09B parameter language model trained entirely from scratch (custom tokenizer, custom corpus, no inherited weights). This repo holds the raw pretrained checkpoint (v9 lineage), before any supervised fine-tuning.

Uses the Qwen3 architecture for serving compatibility. Shares no weights with Qwen: the tokenizer (custom 32k SentencePiece) and every parameter were trained from zero.

Note: this is the raw base model. It completes text; it does not follow instructions. The post-trained sibling (rivet-1b-it), which chats and reasons in <think> blocks, is not currently released.

What this is for

Fine-tuning your own model on top of a from-scratch 1B with a 16K context
Research into small-model pretraining dynamics (full pipeline and data disclosure in the technical report)
A clean, fully-documented provenance chain: every pretraining token is public data or documented

Training lineage

v6 pilot: 6.3B tokens, deliberately undertrained (2x RTX 5090)
v7 main pretrain: ~100B tokens over 7 weeks (from the 283.4B-token corpus), eval loss 1.598 (2x RTX 5090)
v8 context extension: RoPE ABF (theta 100K → 1e6) to 16K context, +3B long-doc tokens (2x H100)
v9 "intelligence run": +20B tokens reweighted toward reasoning/math/code, eval loss 1.477. This checkpoint.

Total: ~129B tokens trained from the 387.5B-token pool (full composition in the technical report).

Training logs

Raw TensorBoard event files for the v7 main pretrain and v9 intelligence run are in tensorboard/ (the report's loss-curve figure is generated from these).

Model details


Params	1,086,422,528
Architecture	Qwen3ForCausalLM (from-scratch weights)
Hidden / layers	2048 / 22
Heads	16 query / 8 KV (GQA), head_dim 128
FFN	5504 (SwiGLU)
Vocab	32000 (custom SentencePiece)
Context	16384 (RoPE θ=1e6; YaRN-extrapolable to ~64K)
Tokenizer	custom 32k; `<think>`=4, `</think>`=5, `<

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

m = "josh-a/rivet-1b-pt"
tok = AutoTokenizer.from_pretrained(m)
model = AutoModelForCausalLM.from_pretrained(m, dtype=torch.bfloat16).to("cuda").eval()

ids = tok("The capital of New Zealand is", return_tensors="pt").to("cuda")
out = model.generate(**ids, max_new_tokens=20, do_sample=False)
print(tok.decode(out[0][ids["input_ids"].shape[1]:]))
# -> " Wellington" (as of the v9 intelligence run)

Evals

Per-question GSM8K results are in evals/gsm8k_v10_results.jsonl (1,319 rows: question, gold, prediction, raw output tail). Note: GSM8K was run on the post-trained sibling checkpoint (rivet-1b-it, not released), scoring 12.7% (168/1319). Methodology in the technical report.

Limitations

This is a base model: no instruction following, no chat template behaviour, no refusals, no alignment of any kind.
Factually modest (1B parameters); see the technical report for the honest eval picture.

License

Apache-2.0. From-scratch weights; no upstream model license applies.

Downloads last month: 320

Safetensors

Model size

1B params

Tensor type

BF16

Article mentioning josh-a/rivet-1b-pt

Rivet-1B: A From-Scratch 1.09B Reasoning Model

josh-a

•

2 days ago

• 2