Instructions to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="pkpie1234/usdjpy-qwen25-3b-v6_1-gguf",
	filename="usdjpy_qwen25_3b_v6_1_q8.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf
# Run inference directly in the terminal:
llama-cli -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf
# Run inference directly in the terminal:
llama-cli -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

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 pkpie1234/usdjpy-qwen25-3b-v6_1-gguf
# Run inference directly in the terminal:
./llama-cli -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

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 pkpie1234/usdjpy-qwen25-3b-v6_1-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

Use Docker

docker model run hf.co/pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

LM Studio
Jan
Ollama
How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with Ollama:
```
ollama run hf.co/pkpie1234/usdjpy-qwen25-3b-v6_1-gguf
```

Unsloth Studio

How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf 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 pkpie1234/usdjpy-qwen25-3b-v6_1-gguf 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 pkpie1234/usdjpy-qwen25-3b-v6_1-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for pkpie1234/usdjpy-qwen25-3b-v6_1-gguf to start chatting

How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "pkpie1234/usdjpy-qwen25-3b-v6_1-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with Docker Model Runner:
```
docker model run hf.co/pkpie1234/usdjpy-qwen25-3b-v6_1-gguf
```

Lemonade

How to use pkpie1234/usdjpy-qwen25-3b-v6_1-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

Run and chat with the model

lemonade run user.usdjpy-qwen25-3b-v6_1-gguf-{{QUANT_TAG}}

List all available models

lemonade list

USDJPY Qwen 2.5 3B v6.1 — GGUF q8_0

GGUF q8_0 quantization of pkpie1234/usdjpy-qwen25-3b-v6_1 (LoRA fine-tuned Qwen 2.5 3B Instruct).

Designed for Ollama / llama.cpp inference. 3.13 GB.

⚠️ Honest Disclosure

v6.1 was trained on M5 1-hour-horizon scalping calibration that does NOT generalize per 4-year walk-forward validation.

4-year walk-forward (8 chronological folds, 24K bars): 0 robust setups for M5 1h horizon
Real edge identified at H1 (24-48h hold) and D1 (5-10d hold) — see v7 (training pending)

Use v6.1 only for:

Research / education
Z2H integration testing
Paper trading validation

Do NOT use for live trading without independent walk-forward verification.

Full documentation: https://github.com/pkpie1234/v7llm/blob/main/HANDOFF.md

Inference (Ollama)

# Download GGUF + Modelfile
hf download pkpie1234/usdjpy-qwen25-3b-v6_1-gguf --local-dir .

# Register with Ollama
ollama create usdjpy-qwen25-3b-v6_1 -f Modelfile

# Test
ollama run usdjpy-qwen25-3b-v6_1 \
  '{"sym":"USDJPY","tf":"M5","sess":"london","p":154.10,"ema20":154.43,"ema50":154.35,"rsi":32.0,"atr":6.5,"h1c":154.50,"trend":"strong_up","vol":"normal","day_high":155.20,"day_low":154.05,"day_range":115.0,"day_pos":0.043,"regime":"range_extended_low"}'

Expected output (JSON):

{
  "primary_action": "buy",
  "setup_type": "range_fade_buy",
  "sl_pips": 15.0,
  "tp_pips": 30.0,
  "time_stop_minutes": 60,
  "lot_size": 0.02,
  "confidence": 0.69,
  "ev_estimate_pips": 2.78,
  "ev_decision": "take_positive_ev",
  "reasoning": "Regime=range_extended_low allows range_fade_buy; calibrated EV +2.78p.",
  "trade_quality": "B"
}

Inference (llama.cpp)

./llama-cli -m usdjpy_qwen25_3b_v6_1_q8.gguf \
  -p "system prompt + user JSON" \
  -n 512 --temp 0.3

Model Details

Property	Value
Base model	Qwen/Qwen2.5-3B-Instruct
Fine-tune method	QLoRA NF4, r=16, α=32
Quantization (this file)	Q8_0 (3.13GB)
Trainable params	29.93M / 3.12B (0.96%)
Training data	12K samples (M5 OHLC + macro + event playbook)
Epochs	1
Final eval_loss	0.31
Training time	9h 49min on RTX 2070 Super

Training Data Composition (12K samples)

M5 OHLC features (multi-TF)
Z2H ultrashort prompt format
Macro reasoning (DXY/yield/risk)
Event playbook (FOMC/BoJ/NFP/CPI)
Multi-horizon teaching (W1/D1/H4/H1/M5)
Failure-mode QA
Risk validator examples

License

Apache 2.0 (inherits from base model). Use at own risk; no profit guarantees.

Citation

@misc{pkpie1234_usdjpy_v6_1,
  author = {pkpie1234},
  title = {USDJPY Qwen 2.5 3B v6.1 GGUF},
  year = {2026},
  publisher = {HuggingFace},
  url = {https://huggingface.co/pkpie1234/usdjpy-qwen25-3b-v6_1-gguf}
}

Downloads last month: 9

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for pkpie1234/usdjpy-qwen25-3b-v6_1-gguf

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Quantized

(238)

this model