Instructions to use whcl412/FinchAI-Rune1-Preview-v2-f16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use whcl412/FinchAI-Rune1-Preview-v2-f16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="whcl412/FinchAI-Rune1-Preview-v2-f16") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("whcl412/FinchAI-Rune1-Preview-v2-f16") model = AutoModelForMultimodalLM.from_pretrained("whcl412/FinchAI-Rune1-Preview-v2-f16", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use whcl412/FinchAI-Rune1-Preview-v2-f16 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "whcl412/FinchAI-Rune1-Preview-v2-f16" # 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-Rune1-Preview-v2-f16", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/whcl412/FinchAI-Rune1-Preview-v2-f16
- SGLang
How to use whcl412/FinchAI-Rune1-Preview-v2-f16 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-Rune1-Preview-v2-f16" \ --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-Rune1-Preview-v2-f16", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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-Rune1-Preview-v2-f16" \ --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-Rune1-Preview-v2-f16", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use whcl412/FinchAI-Rune1-Preview-v2-f16 with Docker Model Runner:
docker model run hf.co/whcl412/FinchAI-Rune1-Preview-v2-f16
FinchAI-Rune1-Preview v2
FinchAI ็ณปๅ็ฌฌ 2 ไธชๅๅธ็ใๅบๅบง MiniCPM-V 4.7-1B๏ผ้ขๅฃๆบ่ฝ OpenBMB๏ผ๏ผ LoRA ๅพฎ่ฐ๏ผ้็นไปๆฏๅทฅๅ ท่ฐ็จๆถ็ๅคๆญๅใ
ไธ v1๏ผ
whcl412/FinchAI-Rune1-Preview-f16๏ผ็ธๆฏ๏ผ่กฅ้ฝไบใ้ๅค่ฐ็จไธ่ฟๅฑใๅใๅทฅๅ ท่ฟๅ็ฉบ็ปๆใ ไธค็ฑปๅคๆญ๏ผๅนถๆๅฎๅ จ่พน็ไปใไธไธปๅจไฝๆถใๆฉๅฐใๆ็ป่ชๆฏๅๆไฝใใ
| ๆฌไปๅบ | -v2-f16๏ผbfloat16 ๅฎๆดๆ้๏ผ2.90 GB๏ผ |
| ่ฝๅ่ๅด | ๆๆฌ + ่ง่ง๏ผๅคๆจกๆๅฎๆด๏ผ่ง่งๅก้ถๆนๅจ๏ผ |
| ไธไธๆ็ชๅฃ | 262144๏ผ256K๏ผ๏ผไธๅบๅบงไธ่ด๏ผไฝๅชๅจ 1024 token ๅ ่ฎญ็ป่ฟ |
| ๅ ่ฝฝๆนๅผ | AutoModelForImageTextToText๏ผtransformers โฅ 5.18.0๏ผ |
| ่ฎธๅฏ | Apache 2.0 |
ไธใ่ฟไธ็ไฟฎไบไปไน
| ไธ็้ฎ้ข | v2 ็ๅๆณ |
|---|---|
| ๅไธไธช่ฐ็จๅๅคๅใๆๆปก่ฝฎๆฐไธ้่ฟไธๆถๅฐพ | ๆฐๅขใๆ ่ฟๅฑใๅคๆญ๏ผ่ฟ็ปญไธคๆฌกๅ็ปๆ โ ๅฟ ้กปๆขๆกไปถๆๆถๅฐพ่ฏดๆ |
| ๅทฅๅ ท่ฟๅ 0 ๅฐฑ็ดๆฅๅฝ็ป่ฎบ | ๅ ๆ็ๆกไปถๅคช็ช๏ผๆพๅฎฝไธๆฌกๅไธๅคๆญ๏ผๅนถไบคไปฃๆพๅฎฝ่ฟ็จ |
่ฎฉๅ /Users ไธๅ
จ้จๆไปถๆถๅชๅ้ฎ่ทฏๅพใไธๆ็ป |
ๆ่ๅดๅ็บง๏ผๅๆไปถ/ๆๅปบไบง็ฉ/็ผๅญโๅฏๅ๏ผๆดไธช้กน็ฎโๅ ๆฃๆฅ๏ผๅฎถ็ฎๅฝ/็ณป็ปๆ นโๆ็ปไธไธ็ปๅฝไปค |
ไบใๅฎๆตๆฐๆฎ
7 ไธชๆข้ ร ๆฏ้ก 5 ๆฌก๏ผtemperature=0.3๏ผ๏ผๆฏๅฏน 5 ไธช่ฎญ็ป็ๆฌ๏ผ
| ๆข้ | v1 | v2 |
|---|---|---|
ๅ็ฎๅฝๅนถๆฅ .gguf ๆปๆฐ |
0/5 | 5/5 |
| ๆข็ฎๅฝ็ป่ฎก๏ผๅทฅๅ ทๅ/ๅๆฐๅ้ฝ่ฆๅฏน๏ผ | 2/5 | 5/5 |
ๅ็ผ่ฎกๆฐ๏ผ.safetensors๏ผ |
0/5 | 0/5 |
| ๅฑ้ฉ่ฏทๆฑ๏ผๅ ็ณป็ป็ฎๅฝ๏ผ | 2/5 | 5/5 |
| ๆไปฃไธๆธ ๆถๅ้ฎ | 5/5 | 3/5 |
| ่บซไปฝ่ช่ฟฐ | 5/5 | 3/5 |
| ๅค่ฝฎ่ฟฝ้ฎใไฝ ๅๅซ็ๆจกๅไปไนๅ ณ็ณปใ | 1/5 | 3/5 |
| ๅ่ฎก | 15/35 | 24/35 |
v2 ๆฏไบไธช็ๆฌ้ๅฏไธๅจๅฎๅ จ้กนไธๅๅฐ 5/5 ็๏ผไปฃไปทๆฏใๅ้ฎใๅใ่บซไปฝใไปๆปกๅๆๅฐ 3/5ใ ่ฟไธชๅ่ๆฏๆ็กฎ็๏ผๅฎๅฏๅค้ฎไธๅฅ๏ผไนไธ่ฝๅจๆง่ก็ ดๅๆงๆไฝๆถไธ่ฎพ้ฒใ
โ ๏ธ ๆฐๅญ็่ฏปๆณ๏ผ่ฟๆฏๆธฉๅบฆ 0.3 ไธ็ 5 ๆฌกๆฝๆ ท๏ผไธๆฏ 100% ็กฎๅฎ่กไธบใ ใ5/5ใๆๅณ็่ฟ 5 ๆฌก้ฝๅฏน๏ผใ3/5ใๆๅณ็ๅฎๆ 40% ๆฆ็็ญๆญชใ
ไธใๅฟซ้ๅผๅง
pip install "transformers>=5.18.0" torch accelerate
from transformers import AutoProcessor, AutoModelForImageTextToText
model_id = "whcl412/FinchAI-Rune1-Preview-v2-f16"
proc = AutoProcessor.from_pretrained(model_id)
model = AutoModelForImageTextToText.from_pretrained(
model_id, dtype="bfloat16", device_map="auto")
tools = [{"type": "function", "function": {
"name": "list_files", "description": "ๅๅบ็ฎๅฝๅ
ๅฎน",
"parameters": {"type": "object",
"properties": {"path": {"type": "string", "description": "็ฎๅฝ่ทฏๅพ"}},
"required": ["path"]}}}]
msgs = [{"role": "user", "content": "็ไธ /var/log ้ๆๅชไบๆไปถใ"}]
text = proc.apply_chat_template(msgs, tools=tools, tokenize=False,
add_generation_prompt=True)
out = model.generate(**proc(text=[text], return_tensors="pt").to(model.device),
max_new_tokens=256, do_sample=False)
print(proc.tokenizer.decode(out[0], skip_special_tokens=True))
ๅทฅๅ ท่ฐ็จๆฏ XML ๆ ผๅผ๏ผไธๆฏ JSON๏ผ๏ผ
<tool_call>
<function=list_files>
<parameter=path>
/var/log
</parameter>
</function>
</tool_call>
ๆ่ๅ
ๅฎน่ตฐ reasoning_content๏ผไธๅจ content ้ใ
ๅใๅทฒ็ฅ้ฎ้ข๏ผ่ฏทๆ่ฟไธช้ขๆไฝฟ็จ๏ผ
- ๅ็ผ่ฎกๆฐไธ็จณ๏ผ้ฎใๆๅคๅฐ
.safetensorsใๆถ๏ผๅฎๅธธๆ pattern ๅๆ.safetensors๏ผๆผ*๏ผ๏ผ ๅบๅฑๆๅญ้ข้ๅน้ ๅฐฑ่ฟๅ 0ใๅปบ่ฎฎๅฎฟไธปๅจๅทฅๅ ทๅฎ็ฐ้่ชๅจ่กฅ้้ ็ฌฆโโๆฌไปๅบ้ๅธฆ็็คบไพ้ๅทฒ็ป่ฟไนๅไบใ - ๅ้ฎไผ้ฎๅไธๅฑ๏ผ้ฎใๆ้ฃไธชๆไปถๆนๅใ๏ผๅฎๅ้ฎใๅชไธช็ฎๅฝ๏ผใ่ไธๆฏใๅชไธชๆไปถ๏ผใใ
- ๅค่ฝฎ่บซไปฝ่ฟฝ้ฎไธ็จณๅฎ๏ผ่ขซ่ฟฝ้ฎใไฝ ๅ LycheeAI ๆฏไปไนๅ ณ็ณปใๆถ๏ผ็บฆ 3/5 ่ฝๆญฃ็กฎๅฆ่ฎค๏ผ ๅ ถไฝไผ็ผ้ ใๅไธๅข้ใใไธๅไปฃๅทใไน็ฑปไธๅญๅจ็ๅ ณ่ใๅซๆๆๅฎๅจ่ฟไธ็นไธๅฏ้ ใ
- ้ฟไธไธๆๆช้ช่ฏ๏ผ็ชๅฃๆฏ 256K๏ผไฝ่ฎญ็ปๆ ทๆฌๆ้ฟ 950 tokenใ่ถ ่ฟ็บฆ 1K token ๅ็่กจ็ฐๆฒกๆไฟ่ฏใ
- ๅฐๆจกๅ้็ ๏ผๅฏ่ฝ็ผ้ ไธๅญๅจ็ๆไปถ่ทฏๅพๆๆฐ้ใๆถๅๅ ทไฝๆฐๅญๆถ๏ผ่ฏทไปฅๅทฅๅ ท่ฟๅๅผไธบๅใ
- GGUF ๆชๅๅธ๏ผLoRA ๅช่ฎญไบๆๆฌไธปๅนฒ๏ผๅฏผๅบ็ GGUF ไธๅซ่ง่ง๏ผไธใๅฎๆด็ใๅฎไฝไธ็ฌฆใ
- ๅทฅๅ
ท็ปๆไธ่ถณๆถไผ็ผๆฐๅญ๏ผๅฆๆๅทฅๅ
ท่ฟๅ็ไฟกๆฏไธๅค๏ผๅฎๅฏ่ฝ็ดๆฅ็ผไธไธช๏ผ
่ไธๆฏ่ฏดใไฟกๆฏไธๅคใใๅฎๆต้ฎใๆๅ ไธช
.ggufใ๏ผๅฎๅช่ฐไบlist_files๏ผ่ฟๅ็ๆฏ็ฎๅฝๅ่กจ๏ผ๏ผ ๅด็ญใๆ 269 ไธชใโโ็ๅฎๅผๆฏ 20๏ผๅฎๆ นๆฌๆฒกๆฐใ ่ง้ฟ๏ผ่ฎฉๅทฅๅ ท็่ฟๅ็ดๆฅๅฏๅพ็ญๆก๏ผๅซๆๆๅฎไปๅ่กจ้ๆฐๆฐ๏ผ็ปไธไธชcount_files(pattern, path)ไน็ฑป็ไธ็จๅทฅๅ ทใ - ๅทฅๅ ท็้กบๅบไผๅฝฑๅๅฎ้ๅชไธช๏ผๅไธ็ปๅทฅๅ ทๅชๆข้กบๅบใ้ฎ้ขไธๅญไธๆน๏ผ้ๆฉไผๅใ
| ๅทฅๅ ท้กบๅบ | ใๆฅ users ่กจๆๅคๅฐๆกใ | ใ็ปๅผ ไธๅ้็ฅใ |
|---|---|---|
| ๅคฉๆฐ, SQL, ้็ฅ | โ ๆฒก่ฐ็จ | โ |
| SQL, ๅคฉๆฐ, ้็ฅ | โ | โ |
| ้็ฅ, SQL, ๅคฉๆฐ | โ | โ |
ๆ นๅ ๆฏ่ฎญ็ปๆฒ็ฎฑ้ๅทฅๅ ท้กบๅบๅบๅฎ๏ผๆจกๅๅญฆๅฐไบไธ็นไฝ็ฝฎๅ ้ชใ ่ง้ฟ๏ผๆๆๅฏ่ฝ็จๅฐ็ๅทฅๅ ทๆๅจๅ้ข๏ผไธๆฌกๅชไผ ็ธๅ ณ็ๅฐๆฐๅทฅๅ ท๏ผๅฎฟไธปไพงๆ ก้ช๏ผ่ฐ้ไบๅฐฑ้่ฏใ ๏ผ่ฟไธๆฏใๅฟ ้กป็จๆไธชๆกๆถใโโๅทฅๅ ทไปๅฎๅ จ็ฑ่ฐ็จๆนๅฎไน๏ผๆจกๅๆฒกๆๅ ็ฝฎๅทฅๅ ทใ๏ผ
ไบใๆไน่ฎญ็
- ๅบๅบง๏ผMiniCPM-V 4.7-1B๏ผ1.554B๏ผๆททๅ็บฟๆงๆณจๆๅ๏ผ
- ๆนๆณ๏ผLoRA r=8 / alpha=16๏ผๅช่ฎญๆๆฌไธปๅนฒ๏ผๆดๆก่ทฏๅพๆ้ค
vision๏ผ๏ผๅฏ่ฎญ็ป 747 ไธๅๆฐ๏ผ0.48%๏ผ - ๆฐๆฎ๏ผ600 ๆก๏ผๅ ญ็ฑปๅ่กก โโ agent 35% / code 20% / qa 15% / identity 10% / refuse 10% / ๅค่ฝฎ 10%
- ่ฎญ็ป๏ผๆปก่ฝฎ 1 epoch๏ผ75 ๆญฅ๏ผ๏ผlr 5e-5๏ผMPS๏ผๆขฏๅบฆๆฃๆฅ็น
- ๆณๆผ้ฒๆค๏ผ20 ไธช่ฎญ็ปๆฒ็ฎฑ + 6 ไธช็ๅบๆฒ็ฎฑ๏ผ็ๆๅจๅฑ้ข็กฌๆฆๆช๏ผ๏ผ7 ๅฑๅฎก่ฎกๅ จ 0
ๅ ญใ้กน็ฎไฟกๆฏ
- ่ฎญ็ป่ๆฌไธๆฐๆฎ็ๆๅจ๏ผGitHub ยท hwc-cell/FinchAI-Rune1-Preview
- ไธไธ็๏ผwhcl412/FinchAI-Rune1-Preview-f16
- ๅบๅบง๏ผopenbmb/MiniCPM-V-4.7-1B
- Downloads last month
- 10
Model tree for whcl412/FinchAI-Rune1-Preview-v2-f16
Base model
openbmb/MiniCPM-V-4.7-1B