Instructions to use perletter/dot-125m-identity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use perletter/dot-125m-identity with Transformers:

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

pipe = pipeline("text-generation", model="perletter/dot-125m-identity")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("perletter/dot-125m-identity")
model = AutoModelForCausalLM.from_pretrained("perletter/dot-125m-identity", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use perletter/dot-125m-identity with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf perletter/dot-125m-identity:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf perletter/dot-125m-identity:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf perletter/dot-125m-identity:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf perletter/dot-125m-identity:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf perletter/dot-125m-identity:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf perletter/dot-125m-identity:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf perletter/dot-125m-identity:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf perletter/dot-125m-identity:Q4_K_M

Use Docker

docker model run hf.co/perletter/dot-125m-identity:Q4_K_M

LM Studio
Jan

vLLM

How to use perletter/dot-125m-identity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "perletter/dot-125m-identity"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "perletter/dot-125m-identity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/perletter/dot-125m-identity:Q4_K_M

SGLang

How to use perletter/dot-125m-identity 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 "perletter/dot-125m-identity" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "perletter/dot-125m-identity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "perletter/dot-125m-identity" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "perletter/dot-125m-identity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use perletter/dot-125m-identity with Ollama:
```
ollama run hf.co/perletter/dot-125m-identity:Q4_K_M
```

Unsloth Studio

How to use perletter/dot-125m-identity with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for perletter/dot-125m-identity to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for perletter/dot-125m-identity to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for perletter/dot-125m-identity to start chatting

Atomic Chat new
Docker Model Runner
How to use perletter/dot-125m-identity with Docker Model Runner:
```
docker model run hf.co/perletter/dot-125m-identity:Q4_K_M
```

Lemonade

How to use perletter/dot-125m-identity with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull perletter/dot-125m-identity:Q4_K_M

Run and chat with the model

lemonade run user.dot-125m-identity-Q4_K_M

List all available models

lemonade list

Dot-125M-Identity

An identity-tuned variant of Dot-125M, by Perletter, part of Chirping Waves Limited (Ireland). Same base architecture and pretrained weights, with a short additional fine-tuning pass so the model can name itself and its creator when asked, in a Q: ...\nA: ... prompt format.

Everything about the base model applies here too — see the Dot-125M model card for full pretraining details, benchmarks, and limitations. This card only covers what's different.

What was added

A small supervised fine-tune (~300 packed 512-token blocks: ~150 varied-phrasing identity Q&A pairs + ~150 unrelated plain-text examples mixed in to guard against the model overfitting into injecting its identity into unrelated answers) on top of ckpt_best.pt, 15 epochs, low learning rate (2e-5), loss masked to the answer span only.

How reliable is it?

Honestly: partially, not perfectly. Tested on phrasings not seen during fine-tuning:

Direct/simple phrasings ("What is your name?", "Who made you?") — reliable.
Rephrased/indirect phrasings ("Who exactly are you?", "I'm curious, who made you?") — correct on most tries, wrong or missing on some (sampling-dependent — this is a 133.7M model, not a large instruction-tuned one).
Non-identity questions — verified no bleed-through in direct testing (the model doesn't start injecting "I'm Dot-125M" into unrelated answers), which was the main risk this fine-tune's mixed-data design was meant to prevent.
One inconsistency worth disclosing plainly: a quick GGUF (llama-cli) spot-check using different default sampling settings than the direct-PyTorch tests failed to recall the identity fact on one sample. The safetensors and GGUF weights are verified byte-parity/near-parity identical (0.0 logit diff on export, <0.2% bpb quantization delta) — this looks like ordinary sampling variance on an already-imperfect (not 100%) fine-tune, not a quantization bug, but it means: don't expect this to work every single time. Use lower temperature / greedy decoding for more consistent recall if that matters for your use case.

If you need this to be fully reliable rather than "mostly," that needs a larger/longer SFT pass than this one, which was intentionally kept small and disclosed as such.

How to use

Same as the base model — swap the repo name:

from transformers import AutoModelForCausalLM, AutoTokenizer

tok = AutoTokenizer.from_pretrained("perletter/Dot-125M-Identity")
model = AutoModelForCausalLM.from_pretrained("perletter/Dot-125M-Identity")

prompt = "Q: What is your name?\nA:"
inputs = tok(prompt, return_tensors="pt")
out = model.generate(**inputs, max_new_tokens=30)
print(tok.decode(out[0], skip_special_tokens=True))

llama-cli -m model-Q8_0.gguf -p "Q: What is your name?\nA:" -n 30

License

Apache 2.0, same as the base model — see LICENSE. Training code not included.

Downloads last month: 70

Safetensors

Model size

0.1B params

Tensor type

F32