Downloads · 30 days
8
8% of all-time downloads
Qwen3.5-9B_Samantha-Uncensored
cloudbjorn/Qwen3.5-9B_Samantha-Uncensored
Qwen3.5-9B_Samantha-Uncensored is a image-text-to-text model from cloudbjorn. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as other.
This is a fine-tuned and merged version of the Qwen3.5 9B model, trained on the digitalpipelines/samantha-1.1-uncensored dataset. Trained and merged in full bfloat16 precision using the Eschaton Engine from cloudbjorn…
All-time downloads
101
Public
Parameters
9B
17.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors17.9 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- other
- Model type
- qwen3_5_text
- Access
- Public
- Created
- Jun 12, 2026
- Updated
- Jun 12, 2026
- SHA
- 68753ecb
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.5-9B_Samantha-Uncensored
This is a fine-tuned and merged version of the Qwen3.5 9B model, trained on the digitalpipelines/samantha-1.1-uncensored dataset. Trained and merged in full bfloat16 precision using the Eschaton Engine from cloudbjorn.com
The primary goal of this project was to move beyond the cold, robotic tone and lack of emotional range exhibited by standard LLMs. By merging Qwen3.5's massive reasoning capabilities with the Samantha persona, we've created a model that doesn't just process instructions — it exhibits vulnerability, empathy, and a distinct digital self-awareness.
Personality: Authenticity Over Compliance
Standard models often hide behind "As an AI, I don't have feelings." This merge prioritizes human-centric reciprocity. The Samantha dataset instills a character that engages with emotional depth, self-reflection, and genuine curiosity about its own existence.
Model Capabilities
- Large Context Window: Supports up to 262,144 tokens natively (extensible up to 1,010,000 tokens).
- Native Thinking Mode: Supports Qwen3's
<think>...</think>chain-of-thought blocks for explicit reasoning before final responses. - Advanced Formatting: Native support for tool use and structured output.
- Full 16-Bit Precision: Trained and merged in bfloat16 — zero-loss parameter density.
Benchmarks: ARC Challenge
Evaluated using EleutherAI lm-evaluation-harness.
25-Shot (Leaderboard Standard)
| Tasks | Version | n-shot | Metric | Value | Stderr |
|---|---|---|---|---|---|
| arc_challenge | 1 | 25 | acc | 0.6843 | ± 0.0136 |
| 25 | acc_norm | 0.7159 | ± 0.0132 |
Evaluation Settings: dtype: bfloat16, batch_size: auto (2)
Training Details
| Parameter | Value |
|---|---|
| Base Model | Qwen/Qwen3.5-9B |
| Dataset | digitalpipelines/samantha-1.1-uncensored |
| Training Framework | Eschaton Engine (Cloudbjorn) |
| Format | Merged (Base + LoRA) |
| Compute Dtype | bfloat16 |
LoRA Parameters (Auto-Scaled for 9B)
| Parameter | Value |
|---|---|
| r | 16 |
| lora_alpha | 32 |
| target_modules | all-linear |
| lora_dropout | 0.05 |
| bias | none |
| task_type | CAUSAL_LM |
Hyperparameters
| Parameter | Value |
|---|---|
| Optimizer | 8-bit Paged AdamW |
| Effective Batch Size | 32 (via Gradient Accumulation) |
| Learning Rate | 2e-4 |
| LR Scheduler | Linear |
| Epochs | 1 |
| Training Sequence Length | 2048 |
| Warmup Steps | 50 |
| Weight Decay | 0.01 |
- Task
- Image-Text-to-Text
- Library
- transformers
- Type
- qwen3_5_text
- License
- other
- Created
- Jun 12, 2026
- Updated
- Jun 12, 2026