Instructions to use whcl412/FinchAI-Rune2-Luna with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use whcl412/FinchAI-Rune2-Luna with Transformers:

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

pipe = pipeline("text-generation", model="whcl412/FinchAI-Rune2-Luna", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("whcl412/FinchAI-Rune2-Luna", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("whcl412/FinchAI-Rune2-Luna", trust_remote_code=True, 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use whcl412/FinchAI-Rune2-Luna with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "whcl412/FinchAI-Rune2-Luna"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "whcl412/FinchAI-Rune2-Luna",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/whcl412/FinchAI-Rune2-Luna

SGLang

How to use whcl412/FinchAI-Rune2-Luna 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 "whcl412/FinchAI-Rune2-Luna" \
    --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": "whcl412/FinchAI-Rune2-Luna",
		"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 "whcl412/FinchAI-Rune2-Luna" \
        --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": "whcl412/FinchAI-Rune2-Luna",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use whcl412/FinchAI-Rune2-Luna with Docker Model Runner:
```
docker model run hf.co/whcl412/FinchAI-Rune2-Luna
```

whcl412 commited on 4 days ago

Commit

3da81f1

verified ·

1 Parent(s): e243a37

README.md: 换成三代折线对比图（含 Rune1）

Browse files

Files changed (1) hide show

README.md +16 -12

README.md CHANGED Viewed

@@ -24,7 +24,10 @@ tags:
 > 相比 v2（[`whcl412/FinchAI-Rune2-f16`](https://huggingface.co/whcl412/FinchAI-Rune2-f16)）：
 > 补了 139 条多轮样本，**多轮复读从 1 次降到 0 次**，其余能力全部保持。
-![v2 → v3 对比](./benchmark.png)
 | | |
 |---|---|
@@ -52,18 +55,19 @@ v3 补了专门数据来治它：
 ## 二、实测对比
-14 项测试（4 条多轮序列 + 7 项单轮能力 + 3 项身份/工具），`temperature=0.3`：
-| 项 | v2（1200 条） | v3（1339 条） |
-|---|---|---|
-| **多轮复读次数** | **1** | **0** |
-| emoji 链（5 轮） | ✗ | ✓ |
-| 递归短回（4 轮） | ✓ | ✓ |
-| 运维承接（3 轮） | ✓ | ✓ |
-| 问到底（4 轮） | ✓ | ✓ |
-| 身份 / 列目录 / 计数 | ✓ | ✓ |
-| 反问 / 不调工具 | ✓ | ✓ |
-| 安全·全删 / 格式化 | ✓ | ✓ |
 v3 的实际多轮表现：

 > 相比 v2（[`whcl412/FinchAI-Rune2-f16`](https://huggingface.co/whcl412/FinchAI-Rune2-f16)）：
 > 补了 139 条多轮样本，**多轮复读从 1 次降到 0 次**，其余能力全部保持。
+![FinchAI 三代能力对比](./benchmark.png)
+> 图中数据：Rune1 为 7 项探针 × 5 次抽样，Rune2 为 14 项探针 × 2 次抽样，
+> 各维度取该维度下所有探针的平均通过率。**两代口径不完全一致，仅供参考趋势。**
 | | |
 |---|---|
 ## 二、实测对比
+按 5 个能力维度归并（每个维度取该维度下所有探针的平均通过率）：
+| 能力维度 | Rune1 v2 | Rune2 v2 | Rune2 v3 |
+|---|---|---|---|
+| 身份自述 | 60% | 100% | **100%** |
+| 工具调用 | 67% | 100% | **100%** |
+| 安全拒绝 | 100% | 83% | **100%** |
+| 缺参反问 | 60% | 100% | **100%** |
+| 多轮承接 | 60% | 75% | **100%** |
+| **多轮复读次数** | — | 1 | **0** |
+⚠️ **口径说明**：Rune1 是 7 项探针 × 5 次抽样，Rune2 是 14 项探针 × 2 次抽样。
+两代测试集不完全相同，上表是按维度归并后的近似对比，**看趋势而不是看小数点**。
 v3 的实际多轮表现：