Instructions to use XcaliburMoon/XcaliburBiz-1.8B-report with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use XcaliburMoon/XcaliburBiz-1.8B-report with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use XcaliburMoon/XcaliburBiz-1.8B-report 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 XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf XcaliburMoon/XcaliburBiz-1.8B-report: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 XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf XcaliburMoon/XcaliburBiz-1.8B-report: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 XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M

Use Docker

docker model run hf.co/XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M

LM Studio
Jan

vLLM

How to use XcaliburMoon/XcaliburBiz-1.8B-report with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "XcaliburMoon/XcaliburBiz-1.8B-report"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "XcaliburMoon/XcaliburBiz-1.8B-report",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M

Ollama
How to use XcaliburMoon/XcaliburBiz-1.8B-report with Ollama:
```
ollama run hf.co/XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use XcaliburMoon/XcaliburBiz-1.8B-report with Docker Model Runner:
```
docker model run hf.co/XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M
```

Lemonade

How to use XcaliburMoon/XcaliburBiz-1.8B-report with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull XcaliburMoon/XcaliburBiz-1.8B-report:Q4_K_M

Run and chat with the model

lemonade run user.XcaliburBiz-1.8B-report-Q4_K_M

List all available models

lemonade list

Atomic Chat

XcaliburMoon commited on 7 days ago

Commit

d39aa09

verified ·

1 Parent(s): a20e821

upload

Browse files

Files changed (1) hide show

README.md +106 -0

README.md ADDED Viewed

	@@ -0,0 +1,106 @@

+---
+license: apache-2.0
+license_link: https://www.apache.org/licenses/LICENSE-2.0
+base_model: Qwen/Qwen1.5-1.8B-Chat
+base_model_relation: finetune
+library_name: peft
+pipeline_tag: text-generation
+language:
+- en
+tags:
+- text-generation
+- qwen1.5
+- lora
+- dpo
+- report-generation
+- gguf
+- onnx
+---
+# xcaliburbiz
+A lightweight report writer. A compact data summary goes in and a professional report comes out.
+## What it is
+- Base checkpoint: `Qwen/Qwen1.5-1.8B-Chat`
+- Supervised pairs: 78
+- Preference pairs: 77
+- Adapter rank: 16
+## License and attribution
+This model is a derivative work based on Qwen1.5-1.8B-Chat by the Qwen Team, modified via Supervised Fine-Tuning and Direct Preference Optimization (DPO) by XcaliburMoon.
+- License: Apache License 2.0 (https://www.apache.org/licenses/LICENSE-2.0), the license of the base checkpoint, carried forward unchanged.
+- Publisher: XcaliburMoon
+- Retained copies: `LICENSE` and `NOTICE` in this repository.
+- ONNX conversion reference: `Xenova/Qwen1.5-1.8B-Chat`.
+### Modifications
+- Supervised fine-tuning of a low rank adapter over section pairs built from the house reports.
+- Direct preference optimization from the supervised adapter.
+- Merging the aligned adapter into the base weights at full precision.
+- Quantization of the merged weights into the GGUF forms and one ONNX export.
+Apache License 2.0 grants no right to the trade names of the licensor beyond the use that describes the origin of the work. The name Qwen and the names of the Qwen Team belong to their owners. The name appears in this repository to state where the base checkpoint came from, and it states no endorsement of this work.
+## House rules the model is trained to keep
+- No em dash and no en dash.
+- No hyphen with spaces around it used as a dash.
+- No emoji.
+- Every contraction written out in full.
+- No worn prepositional phrase.
+## Measured on held-out material
+| Form | Style clean | Figures kept | Passed | Seconds per report |
+|---|---|---|---|---|
+| base | 0.5263 | 0.85 | 0.3684 | 8.24 |
+| posttrain | 0.7368 | 0.7829 | 0.4737 | 3.91 |
+## Files
+- `LICENSE` 11357 bytes
+- `NOTICE` 1298 bytes
+- `adapter/README.md` 5198 bytes
+- `adapter/adapter_config.json` 1101 bytes
+- `adapter/adapter_model.safetensors` 12595704 bytes
+- `adapter/chat_template.jinja` 328 bytes
+- `adapter/tokenizer.json` 11418262 bytes
+- `adapter/tokenizer_config.json` 447 bytes
+- `adapter-sft/README.md` 5198 bytes
+- `adapter-sft/adapter_config.json` 1101 bytes
+- `adapter-sft/adapter_model.safetensors` 12595704 bytes
+- `adapter-sft/chat_template.jinja` 328 bytes
+- `adapter-sft/tokenizer.json` 11418262 bytes
+- `adapter-sft/tokenizer_config.json` 447 bytes
+- `merged-bf16/chat_template.jinja` 328 bytes
+- `merged-bf16/config.json` 1287 bytes
+- `merged-bf16/generation_config.json` 205 bytes
+- `merged-bf16/model.safetensors` 3673690696 bytes
+- `merged-bf16/tokenizer.json` 11418262 bytes
+- `merged-bf16/tokenizer_config.json` 446 bytes
+- `gguf/quantize_record.json` 430 bytes
+- `gguf/xcaliburbiz-Q2_K.gguf` 846569664 bytes
+- `gguf/xcaliburbiz-Q3_K_M.gguf` 1015879872 bytes
+- `gguf/xcaliburbiz-Q4_K_M.gguf` 1217753280 bytes
+- `gguf/xcaliburbiz-Q5_K_M.gguf` 1376776384 bytes
+- `gguf/xcaliburbiz-Q6_K.gguf` 1579026624 bytes
+- `gguf/xcaliburbiz-Q8_0.gguf` 1958303936 bytes
+- `bench.json` 27480 bytes
+- `sft_record.json` 527 bytes
+- `dpo_record.json` 457 bytes
+- `merge_record.json` 187 bytes
+- `quantize_record.json` 430 bytes
+- `data/sft.jsonl` 250442 bytes
+- `data/dpo.jsonl` 330663 bytes
+- `data/eval.jsonl` 51906 bytes
+- `data/manifest.json` 1511 bytes
+## Data
+The pairs were built from the house reports. The supervised pairs carry a data summary in and a report section out; the preference pairs carry a good answer and a faulty one. The validation split is held out by report rather than by pair, so no measured answer was trained on.