Text Generation
Transformers
Safetensors
English
qwen2
dating
relationships
advice
companion
chat
fine-tuned
qwen
spiceechat
conversational
text-generation-inference
Instructions to use SpiceeChat/Cinder-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SpiceeChat/Cinder-1.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="SpiceeChat/Cinder-1.5B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("SpiceeChat/Cinder-1.5B") model = AutoModelForCausalLM.from_pretrained("SpiceeChat/Cinder-1.5B") 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=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use SpiceeChat/Cinder-1.5B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "SpiceeChat/Cinder-1.5B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SpiceeChat/Cinder-1.5B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/SpiceeChat/Cinder-1.5B
- SGLang
How to use SpiceeChat/Cinder-1.5B 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 "SpiceeChat/Cinder-1.5B" \ --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": "SpiceeChat/Cinder-1.5B", "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 "SpiceeChat/Cinder-1.5B" \ --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": "SpiceeChat/Cinder-1.5B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use SpiceeChat/Cinder-1.5B with Docker Model Runner:
docker model run hf.co/SpiceeChat/Cinder-1.5B
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,158 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- dating
|
| 7 |
+
- relationships
|
| 8 |
+
- advice
|
| 9 |
+
- companion
|
| 10 |
+
- chat
|
| 11 |
+
- fine-tuned
|
| 12 |
+
- qwen
|
| 13 |
+
- spiceechat
|
| 14 |
+
pipeline_tag: text-generation
|
| 15 |
+
model-index:
|
| 16 |
+
- name: Cinder-1.5B
|
| 17 |
+
results: []
|
| 18 |
+
datasets:
|
| 19 |
+
- SpiceeChat/OkCupid-59k-Anonymized-Profiles
|
| 20 |
+
- SpiceeChat/Dating-App-Behavior-Dataset
|
| 21 |
+
- SpiceeChat/Dating-App-59k-Anonymized-Profiles
|
| 22 |
+
- SpiceeChat/Lovoo-4k-Profiles
|
| 23 |
+
library_name: transformers
|
| 24 |
+
---
|
| 25 |
+
|
| 26 |
+
<p align="center">
|
| 27 |
+
<img src="https://huggingface.co/SpiceeChat/Bio2Tags-Qwen3.5-4B-SFT/resolve/main/Spiceechat.png"
|
| 28 |
+
alt="SpiceeChat"
|
| 29 |
+
width="1100"
|
| 30 |
+
height="1000"
|
| 31 |
+
style="border-radius: 50%; object-fit: cover;">
|
| 32 |
+
</p>
|
| 33 |
+
|
| 34 |
+
<p align="center">
|
| 35 |
+
<a href="https://huggingface.co/Qwen"><img src="https://img.shields.io/badge/Qwen-2.5-blue?logo=huggingface" alt="Qwen2.5"></a>
|
| 36 |
+
<a href="https://github.com/unslothai/unsloth"><img src="https://img.shields.io/badge/FineβTuned-QLoRA-green" alt="FineβTuned"></a>
|
| 37 |
+
<a href="https://huggingface.co/SpiceeChat"><img src="https://img.shields.io/badge/SpiceeChat-π₯-orange" alt="SpiceeChat"></a>
|
| 38 |
+
<a href="https://www.apache.org/licenses/LICENSE-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-yellow" alt="License"></a>
|
| 39 |
+
</p>
|
| 40 |
+
|
| 41 |
+
---
|
| 42 |
+
|
| 43 |
+
# π₯ Cinder-1.5B β Your AI Companion for Love & Relationships
|
| 44 |
+
|
| 45 |
+
**Cinder** is a 1.5-billion-parameter conversational AI fine-tuned by **SpiceeChat** to be your personal companion for all things dating, relationships, and emotional connection. Think of her as the friend you text when love gets confusing β part advisor, part confidant, all heart.
|
| 46 |
+
|
| 47 |
+
---
|
| 48 |
+
|
| 49 |
+
## π¬ What Cinder Can Do
|
| 50 |
+
|
| 51 |
+
| Capability | Description |
|
| 52 |
+
|------------|-------------|
|
| 53 |
+
| π§βπ€βπ§ **Partner Matching** | Analyze profiles and suggest ideal partner types |
|
| 54 |
+
| π **Breakup Support** | Compassionate advice for healing and moving forward |
|
| 55 |
+
| π **Communication Tips** | Help with difficult conversations and expressing feelings |
|
| 56 |
+
| π **Profile Analysis** | Understand what dating profiles really say about a person |
|
| 57 |
+
| π§ **Self-Discovery** | Help you figure out what you truly want in a relationship |
|
| 58 |
+
| π€ **Emotional Support** | A safe, non-judgmental space to talk about anything |
|
| 59 |
+
|
| 60 |
+
---
|
| 61 |
+
|
| 62 |
+
## π§ Who Is Cinder?
|
| 63 |
+
|
| 64 |
+
> **"Who are you?"**
|
| 65 |
+
>
|
| 66 |
+
> *"I'm Cinder. Think of me as the friend you text when love gets confusing β part advisor, part confidant, all heart. I was built by SpiceeChat to help people navigate the messy, beautiful world of dating and relationships. I help you find your ideal partner and work through every relationship problem along the way."*
|
| 67 |
+
|
| 68 |
+
---
|
| 69 |
+
|
| 70 |
+
## π οΈ Technical Details
|
| 71 |
+
|
| 72 |
+
| Detail | Value |
|
| 73 |
+
|--------|-------|
|
| 74 |
+
| **Base Model** | `Qwen/Qwen2.5-1.5B-Instruct` |
|
| 75 |
+
| **Fine-Tuning Method** | QLoRA (Unsloth) |
|
| 76 |
+
| **Training Data** | Curated mix of dating profiles, relationship dialogues, and identity grounding |
|
| 77 |
+
| **Sequence Length** | 2048 tokens |
|
| 78 |
+
| **Precision** | FP16 (merged) |
|
| 79 |
+
| **LoRA Rank** | 16 |
|
| 80 |
+
| **Trainable Params** | 18.5M (1.18% of total) |
|
| 81 |
+
| **License** | Apache 2.0 |
|
| 82 |
+
|
| 83 |
+
---
|
| 84 |
+
|
| 85 |
+
## π Training Data Sources
|
| 86 |
+
|
| 87 |
+
| Source | Description |
|
| 88 |
+
|--------|-------------|
|
| 89 |
+
| ποΈ **Custom JSONL files** | Curated conversation datasets for dialogue style |
|
| 90 |
+
| π **OkCupid-59k** | 59,000 anonymized dating profiles |
|
| 91 |
+
| π± **Dating-App-Behavior-Dataset** | Real user behavior patterns |
|
| 92 |
+
| π **Dating-App-59k-Anonymized-Profiles** | Broad, diverse profile data |
|
| 93 |
+
| π¬ **Lovoo profiles** | Raw dating bios for authentic language |
|
| 94 |
+
|
| 95 |
+
---
|
| 96 |
+
|
| 97 |
+
## π How to Use
|
| 98 |
+
|
| 99 |
+
```python
|
| 100 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 101 |
+
|
| 102 |
+
model_id = "SpiceeChat/Cinder-1.5B"
|
| 103 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 104 |
+
model = AutoModelForCausalLM.from_pretrained(
|
| 105 |
+
model_id,
|
| 106 |
+
torch_dtype="auto",
|
| 107 |
+
device_map="auto",
|
| 108 |
+
)
|
| 109 |
+
|
| 110 |
+
messages = [
|
| 111 |
+
{"role": "user", "content": "I just went through a bad breakup. What should I do?"}
|
| 112 |
+
]
|
| 113 |
+
|
| 114 |
+
inputs = tokenizer.apply_chat_template(
|
| 115 |
+
messages,
|
| 116 |
+
tokenize=True,
|
| 117 |
+
add_generation_prompt=True,
|
| 118 |
+
return_tensors="pt"
|
| 119 |
+
).to(model.device)
|
| 120 |
+
|
| 121 |
+
outputs = model.generate(
|
| 122 |
+
input_ids=inputs,
|
| 123 |
+
max_new_tokens=200,
|
| 124 |
+
temperature=0.7,
|
| 125 |
+
do_sample=True,
|
| 126 |
+
)
|
| 127 |
+
|
| 128 |
+
response = tokenizer.decode(outputs[0][inputs.shape[-1]:], skip_special_tokens=True)
|
| 129 |
+
print(response)
|
| 130 |
+
```
|
| 131 |
+
|
| 132 |
+
---
|
| 133 |
+
|
| 134 |
+
## π·οΈ Built by SpiceeChat
|
| 135 |
+
|
| 136 |
+
Cinder is part of the **SpiceeChat** ecosystem β tools and AI designed to help people find love, build meaningful relationships, and navigate the complexities of modern dating.
|
| 137 |
+
|
| 138 |
+
- π **Website**: [dating-fatigue.com](https://dating-fatigue.com)
|
| 139 |
+
- π€ **Soulmate Oracle**: Live on Hugging Face Spaces
|
| 140 |
+
- π **Organization**: [SpiceeChat on Hugging Face](https://huggingface.co/SpiceeChat)
|
| 141 |
+
|
| 142 |
+
---
|
| 143 |
+
|
| 144 |
+
## β οΈ Disclaimer
|
| 145 |
+
|
| 146 |
+
Cinder is an AI companion, **not a licensed therapist**. She's here to listen, support, and offer perspective β but for serious mental health concerns, please seek help from a qualified professional.
|
| 147 |
+
|
| 148 |
+
---
|
| 149 |
+
|
| 150 |
+
## π License
|
| 151 |
+
|
| 152 |
+
Released under the **Apache 2.0** license. Free to use, modify, and share β just give credit to SpiceeChat.
|
| 153 |
+
|
| 154 |
+
---
|
| 155 |
+
|
| 156 |
+
<div align="center">
|
| 157 |
+
<sub>Made with β€οΈ by SpiceeChat</sub>
|
| 158 |
+
</div>
|