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 6 days ago

Commit

8750b7b

verified ·

1 Parent(s): aac318c

upload

Browse files

Files changed (1) hide show

dpo_record.json +167 -89

dpo_record.json CHANGED Viewed

@@ -4,227 +4,305 @@
   "sft_adapter": "/workspace/xcaliburbiz/out/sft/adapter",
   "init_adapter": "/workspace/xcaliburbiz/out/sft/adapter",
   "beta": 0.1,
-  "pairs": 1263,
   "epochs": 1.0,
-  "steps": 158,
   "max_seq_len": 1280,
   "history": [
     {
       "step": 5,
       "epoch": 0,
-      "loss": 0.6056,
-      "reward_accuracy": 0.725,
-      "lr": 4.999e-05
     },
     {
       "step": 10,
       "epoch": 0,
-      "loss": 0.2826,
-      "reward_accuracy": 0.925,
-      "lr": 4.981e-05
     },
     {
       "step": 15,
       "epoch": 0,
-      "loss": 0.1084,
-      "reward_accuracy": 0.975,
-      "lr": 4.937e-05
     },
     {
       "step": 20,
       "epoch": 0,
-      "loss": 0.0615,
-      "reward_accuracy": 0.975,
-      "lr": 4.868e-05
     },
     {
       "step": 25,
       "epoch": 0,
-      "loss": 0.1313,
-      "reward_accuracy": 0.925,
-      "lr": 4.774e-05
     },
     {
       "step": 30,
       "epoch": 0,
-      "loss": 0.1031,
-      "reward_accuracy": 0.95,
-      "lr": 4.657e-05
     },
     {
       "step": 35,
       "epoch": 0,
-      "loss": 0.1219,
-      "reward_accuracy": 0.875,
-      "lr": 4.517e-05
     },
     {
       "step": 40,
       "epoch": 0,
-      "loss": 0.14,
-      "reward_accuracy": 0.9,
-      "lr": 4.356e-05
     },
     {
       "step": 45,
       "epoch": 0,
-      "loss": 0.145,
-      "reward_accuracy": 0.875,
-      "lr": 4.175e-05
     },
     {
       "step": 50,
       "epoch": 0,
-      "loss": 0.1263,
-      "reward_accuracy": 0.925,
-      "lr": 3.978e-05
     },
     {
       "step": 55,
       "epoch": 0,
-      "loss": 0.0707,
-      "reward_accuracy": 0.975,
-      "lr": 3.765e-05
     },
     {
       "step": 60,
       "epoch": 0,
-      "loss": 0.0747,
-      "reward_accuracy": 0.925,
-      "lr": 3.539e-05
     },
     {
       "step": 65,
       "epoch": 0,
-      "loss": 0.0595,
-      "reward_accuracy": 0.95,
-      "lr": 3.302e-05
     },
     {
       "step": 70,
       "epoch": 0,
-      "loss": 0.0581,
       "reward_accuracy": 0.975,
-      "lr": 3.056e-05
     },
     {
       "step": 75,
       "epoch": 0,
-      "loss": 0.0478,
       "reward_accuracy": 0.975,
-      "lr": 2.805e-05
     },
     {
       "step": 80,
       "epoch": 0,
-      "loss": 0.0656,
-      "reward_accuracy": 0.95,
-      "lr": 2.551e-05
     },
     {
       "step": 85,
       "epoch": 0,
-      "loss": 0.0316,
-      "reward_accuracy": 0.975,
-      "lr": 2.296e-05
     },
     {
       "step": 90,
       "epoch": 0,
-      "loss": 0.0406,
-      "reward_accuracy": 1.0,
-      "lr": 2.044e-05
     },
     {
       "step": 95,
       "epoch": 0,
-      "loss": 0.1151,
-      "reward_accuracy": 0.9,
-      "lr": 1.796e-05
     },
     {
       "step": 100,
       "epoch": 0,
-      "loss": 0.0795,
-      "reward_accuracy": 0.975,
-      "lr": 1.555e-05
     },
     {
       "step": 105,
       "epoch": 0,
-      "loss": 0.0043,
-      "reward_accuracy": 1.0,
-      "lr": 1.324e-05
     },
     {
       "step": 110,
       "epoch": 0,
-      "loss": 0.0387,
       "reward_accuracy": 0.975,
-      "lr": 1.106e-05
     },
     {
       "step": 115,
       "epoch": 0,
-      "loss": 0.1883,
-      "reward_accuracy": 0.9,
-      "lr": 9.02e-06
     },
     {
       "step": 120,
       "epoch": 0,
-      "loss": 0.0638,
-      "reward_accuracy": 0.95,
-      "lr": 7.14e-06
     },
     {
       "step": 125,
       "epoch": 0,
-      "loss": 0.0024,
-      "reward_accuracy": 1.0,
-      "lr": 5.45e-06
     },
     {
       "step": 130,
       "epoch": 0,
-      "loss": 0.121,
-      "reward_accuracy": 0.925,
-      "lr": 3.97e-06
     },
     {
       "step": 135,
       "epoch": 0,
-      "loss": 0.107,
-      "reward_accuracy": 0.9,
-      "lr": 2.7e-06
     },
     {
       "step": 140,
       "epoch": 0,
-      "loss": 0.1091,
       "reward_accuracy": 0.9,
-      "lr": 1.67e-06
     },
     {
       "step": 145,
       "epoch": 0,
-      "loss": 0.0409,
-      "reward_accuracy": 0.975,
-      "lr": 8.7e-07
     },
     {
       "step": 150,
       "epoch": 0,
-      "loss": 0.0707,
       "reward_accuracy": 0.925,
-      "lr": 3.3e-07
     },
     {
       "step": 155,
       "epoch": 0,
-      "loss": 0.0132,
       "reward_accuracy": 1.0,
-      "lr": 5e-08
     }
   ],
   "adapter": "/workspace/xcaliburbiz/out/dpo/adapter"

   "sft_adapter": "/workspace/xcaliburbiz/out/sft/adapter",
   "init_adapter": "/workspace/xcaliburbiz/out/sft/adapter",
   "beta": 0.1,
+  "length_normalized": true,
+  "pairs": 1699,
   "epochs": 1.0,
+  "steps": 212,
   "max_seq_len": 1280,
   "history": [
     {
       "step": 5,
       "epoch": 0,
+      "loss": 0.6631,
+      "reward_accuracy": 0.675,
+      "lr": 5e-05
     },
     {
       "step": 10,
       "epoch": 0,
+      "loss": 0.3937,
+      "reward_accuracy": 0.9,
+      "lr": 4.995e-05
     },
     {
       "step": 15,
       "epoch": 0,
+      "loss": 0.2679,
+      "reward_accuracy": 0.825,
+      "lr": 4.977e-05
     },
     {
       "step": 20,
       "epoch": 0,
+      "loss": 0.1902,
+      "reward_accuracy": 0.95,
+      "lr": 4.944e-05
     },
     {
       "step": 25,
       "epoch": 0,
+      "loss": 0.0975,
+      "reward_accuracy": 0.975,
+      "lr": 4.897e-05
     },
     {
       "step": 30,
       "epoch": 0,
+      "loss": 0.1719,
+      "reward_accuracy": 0.925,
+      "lr": 4.836e-05
     },
     {
       "step": 35,
       "epoch": 0,
+      "loss": 0.1002,
+      "reward_accuracy": 0.95,
+      "lr": 4.762e-05
     },
     {
       "step": 40,
       "epoch": 0,
+      "loss": 0.1618,
+      "reward_accuracy": 0.925,
+      "lr": 4.674e-05
     },
     {
       "step": 45,
       "epoch": 0,
+      "loss": 0.1374,
+      "reward_accuracy": 0.95,
+      "lr": 4.575e-05
     },
     {
       "step": 50,
       "epoch": 0,
+      "loss": 0.1082,
+      "reward_accuracy": 0.95,
+      "lr": 4.463e-05
     },
     {
       "step": 55,
       "epoch": 0,
+      "loss": 0.1333,
+      "reward_accuracy": 0.925,
+      "lr": 4.34e-05
     },
     {
       "step": 60,
       "epoch": 0,
+      "loss": 0.1624,
+      "reward_accuracy": 0.95,
+      "lr": 4.206e-05
     },
     {
       "step": 65,
       "epoch": 0,
+      "loss": 0.1312,
+      "reward_accuracy": 0.925,
+      "lr": 4.063e-05
     },
     {
       "step": 70,
       "epoch": 0,
+      "loss": 0.0348,
       "reward_accuracy": 0.975,
+      "lr": 3.911e-05
     },
     {
       "step": 75,
       "epoch": 0,
+      "loss": 0.0765,
       "reward_accuracy": 0.975,
+      "lr": 3.75e-05
     },
     {
       "step": 80,
       "epoch": 0,
+      "loss": 0.0695,
+      "reward_accuracy": 1.0,
+      "lr": 3.582e-05
     },
     {
       "step": 85,
       "epoch": 0,
+      "loss": 0.1773,
+      "reward_accuracy": 0.925,
+      "lr": 3.408e-05
     },
     {
       "step": 90,
       "epoch": 0,
+      "loss": 0.1113,
+      "reward_accuracy": 0.95,
+      "lr": 3.229e-05
     },
     {
       "step": 95,
       "epoch": 0,
+      "loss": 0.1672,
+      "reward_accuracy": 0.95,
+      "lr": 3.046e-05
     },
     {
       "step": 100,
       "epoch": 0,
+      "loss": 0.1019,
+      "reward_accuracy": 0.925,
+      "lr": 2.859e-05
     },
     {
       "step": 105,
       "epoch": 0,
+      "loss": 0.0402,
+      "reward_accuracy": 0.975,
+      "lr": 2.671e-05
     },
     {
       "step": 110,
       "epoch": 0,
+      "loss": 0.0452,
       "reward_accuracy": 0.975,
+      "lr": 2.481e-05
     },
     {
       "step": 115,
       "epoch": 0,
+      "loss": 0.096,
+      "reward_accuracy": 0.925,
+      "lr": 2.292e-05
     },
     {
       "step": 120,
       "epoch": 0,
+      "loss": 0.0827,
+      "reward_accuracy": 0.975,
+      "lr": 2.103e-05
     },
     {
       "step": 125,
       "epoch": 0,
+      "loss": 0.0931,
+      "reward_accuracy": 0.95,
+      "lr": 1.917e-05
     },
     {
       "step": 130,
       "epoch": 0,
+      "loss": 0.1123,
+      "reward_accuracy": 0.95,
+      "lr": 1.735e-05
     },
     {
       "step": 135,
       "epoch": 0,
+      "loss": 0.0611,
+      "reward_accuracy": 0.975,
+      "lr": 1.556e-05
     },
     {
       "step": 140,
       "epoch": 0,
+      "loss": 0.1014,
       "reward_accuracy": 0.9,
+      "lr": 1.384e-05
     },
     {
       "step": 145,
       "epoch": 0,
+      "loss": 0.1141,
+      "reward_accuracy": 0.925,
+      "lr": 1.217e-05
     },
     {
       "step": 150,
       "epoch": 0,
+      "loss": 0.1395,
       "reward_accuracy": 0.925,
+      "lr": 1.058e-05
     },
     {
       "step": 155,
       "epoch": 0,
+      "loss": 0.0712,
+      "reward_accuracy": 0.95,
+      "lr": 9.08e-06
+    },
+    {
+      "step": 160,
+      "epoch": 0,
+      "loss": 0.1937,
+      "reward_accuracy": 0.9,
+      "lr": 7.66e-06
+    },
+    {
+      "step": 165,
+      "epoch": 0,
+      "loss": 0.0883,
+      "reward_accuracy": 0.95,
+      "lr": 6.35e-06
+    },
+    {
+      "step": 170,
+      "epoch": 0,
+      "loss": 0.0314,
+      "reward_accuracy": 1.0,
+      "lr": 5.14e-06
+    },
+    {
+      "step": 175,
+      "epoch": 0,
+      "loss": 0.123,
+      "reward_accuracy": 0.925,
+      "lr": 4.04e-06
+    },
+    {
+      "step": 180,
+      "epoch": 0,
+      "loss": 0.0458,
+      "reward_accuracy": 0.975,
+      "lr": 3.07e-06
+    },
+    {
+      "step": 185,
+      "epoch": 0,
+      "loss": 0.2712,
+      "reward_accuracy": 0.95,
+      "lr": 2.22e-06
+    },
+    {
+      "step": 190,
+      "epoch": 0,
+      "loss": 0.0805,
+      "reward_accuracy": 0.975,
+      "lr": 1.51e-06
+    },
+    {
+      "step": 195,
+      "epoch": 0,
+      "loss": 0.018,
       "reward_accuracy": 1.0,
+      "lr": 9.3e-07
+    },
+    {
+      "step": 200,
+      "epoch": 0,
+      "loss": 0.0921,
+      "reward_accuracy": 0.95,
+      "lr": 4.9e-07
+    },
+    {
+      "step": 205,
+      "epoch": 0,
+      "loss": 0.0691,
+      "reward_accuracy": 0.95,
+      "lr": 1.8e-07
+    },
+    {
+      "step": 210,
+      "epoch": 0,
+      "loss": 0.0744,
+      "reward_accuracy": 0.975,
+      "lr": 3e-08
     }
   ],
   "adapter": "/workspace/xcaliburbiz/out/dpo/adapter"