Text Generation
Transformers
Safetensors
English
qwen3_5
image-text-to-text
skillflow
agentic-ai
llm-agents
tool-use
lora-merged
conversational
Instructions to use beita6969/SkillFlow-Model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use beita6969/SkillFlow-Model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="beita6969/SkillFlow-Model") 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("beita6969/SkillFlow-Model") model = AutoModelForMultimodalLM.from_pretrained("beita6969/SkillFlow-Model", 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 beita6969/SkillFlow-Model with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "beita6969/SkillFlow-Model" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "beita6969/SkillFlow-Model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/beita6969/SkillFlow-Model
- SGLang
How to use beita6969/SkillFlow-Model 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 "beita6969/SkillFlow-Model" \ --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": "beita6969/SkillFlow-Model", "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 "beita6969/SkillFlow-Model" \ --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": "beita6969/SkillFlow-Model", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use beita6969/SkillFlow-Model with Docker Model Runner:
docker model run hf.co/beita6969/SkillFlow-Model
Add link to paper
#1
by nielsr HF Staff - opened
README.md
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
language:
|
| 3 |
-
- en
|
| 4 |
-
license: apache-2.0
|
| 5 |
-
library_name: transformers
|
| 6 |
-
pipeline_tag: text-generation
|
| 7 |
base_model:
|
| 8 |
- Qwen/Qwen3.5-9B
|
| 9 |
datasets:
|
| 10 |
- beita6969/SkillFlow-Dataset
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
tags:
|
| 12 |
- skillflow
|
| 13 |
- agentic-ai
|
|
@@ -20,6 +20,10 @@ tags:
|
|
| 20 |
|
| 21 |
This repository contains the merged SkillFlow Supervisor model weights.
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## Source
|
| 24 |
|
| 25 |
- Code: https://github.com/beita6969/SkillFlow
|
|
@@ -36,4 +40,4 @@ This repository contains the merged SkillFlow Supervisor model weights.
|
|
| 36 |
- Target modules: `q_proj`, `k_proj`, `v_proj`, `o_proj`
|
| 37 |
- Merge dtype: bfloat16
|
| 38 |
|
| 39 |
-
The training-time backward policy adapter is not merged into this inference model.
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- Qwen/Qwen3.5-9B
|
| 4 |
datasets:
|
| 5 |
- beita6969/SkillFlow-Dataset
|
| 6 |
+
language:
|
| 7 |
+
- en
|
| 8 |
+
library_name: transformers
|
| 9 |
+
license: apache-2.0
|
| 10 |
+
pipeline_tag: text-generation
|
| 11 |
tags:
|
| 12 |
- skillflow
|
| 13 |
- agentic-ai
|
|
|
|
| 20 |
|
| 21 |
This repository contains the merged SkillFlow Supervisor model weights.
|
| 22 |
|
| 23 |
+
## Paper
|
| 24 |
+
|
| 25 |
+
- [SkillFlow: Flow-Driven Recursive Skill Evolution for Agentic Orchestration](https://huggingface.co/papers/2605.14089)
|
| 26 |
+
|
| 27 |
## Source
|
| 28 |
|
| 29 |
- Code: https://github.com/beita6969/SkillFlow
|
|
|
|
| 40 |
- Target modules: `q_proj`, `k_proj`, `v_proj`, `o_proj`
|
| 41 |
- Merge dtype: bfloat16
|
| 42 |
|
| 43 |
+
The training-time backward policy adapter is not merged into this inference model.
|