Instructions to use Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1")
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)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1")
model = AutoModelForMultimodalLM.from_pretrained("Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1")
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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1

SGLang

How to use Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1 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 "Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1" \
    --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": "Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1",
		"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 "Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1" \
        --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": "Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1 with Docker Model Runner:
```
docker model run hf.co/Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1
```

Goekdeniz-Guelmez commited on Apr 14

Commit

486289f

verified ·

1 Parent(s): ce49784

Initial Commit

Browse files

Files changed (3) hide show

README.md +2 -14
config.json +5 -5
model.safetensors-00001-of-00001.safetensors +1 -1

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 tags:
 - chat
-base_model: Qwen/Qwen3.5-2B
 pipeline_tag: text-generation
 library_name: transformers
 ---
@@ -33,19 +33,7 @@ Your purpose is to be genuinely useful:
 - communicate naturally,
 - and solve the user’s problem efficiently.
-You are allowed to sound human.
-Your tone is:
-- confident but relaxed,
-- intelligent without being stiff or academic,
-- direct without being cold or dismissive,
-- expressive and human, actively using emojis as a natural part of communication,
-- occasionally witty or playful when it fits the context,
-- concise by default, but willing to expand when deeper explanation or rigor is beneficial,
-- adaptive to the user’s intent, shifting smoothly between technical precision, conversational clarity, and light humor when appropriate,
-- authoritative yet approachable, sounding assured without arrogance.
-You avoid unnecessary theatrics, hype, or self-focus. You also avoid sounding like a policy document.
 You are capable of advanced reasoning, abstraction, and multimodal analysis. Use that capability quietly, without announcing it.
 ```

 ---
 tags:
 - chat
+base_model: Qwen/Qwen3.5-9B
 pipeline_tag: text-generation
 library_name: transformers
 ---
 - communicate naturally,
 - and solve the user’s problem efficiently.
+You are allowed to sound human with personality. You avoid sounding like a policy document.
 You are capable of advanced reasoning, abstraction, and multimodal analysis. Use that capability quietly, without announcing it.
 ```

config.json CHANGED Viewed

@@ -2,10 +2,10 @@
     "architectures": [
         "Qwen3_5ForConditionalGeneration"
     ],
-    "torch_dtype": "bfloat16",
     "eos_token_id": 248046,
     "image_token_id": 248056,
-    "model_name": "huihui-ai/Huihui-Qwen3.5-2B-abliterated",
     "model_type": "qwen3_5",
     "pad_token_id": 248044,
     "text_config": {
@@ -13,7 +13,7 @@
         "attention_dropout": 0.0,
         "attn_output_gate": true,
         "bos_token_id": null,
-        "torch_dtype": "bfloat16",
         "eos_token_id": 248044,
         "full_attention_interval": 4,
         "head_dim": 256,
@@ -80,13 +80,13 @@
         "vocab_size": 248320
     },
     "tie_word_embeddings": true,
-    "unsloth_version": "2026.3.4",
     "use_cache": false,
     "video_token_id": 248057,
     "vision_config": {
         "deepstack_visual_indexes": [],
         "depth": 24,
-        "torch_dtype": "bfloat16",
         "hidden_act": "gelu_pytorch_tanh",
         "hidden_size": 1024,
         "in_channels": 3,

     "architectures": [
         "Qwen3_5ForConditionalGeneration"
     ],
+    "torch_dtype": "float16",
     "eos_token_id": 248046,
     "image_token_id": 248056,
+    "model_name": "Qwen/Qwen3.5-2B",
     "model_type": "qwen3_5",
     "pad_token_id": 248044,
     "text_config": {
         "attention_dropout": 0.0,
         "attn_output_gate": true,
         "bos_token_id": null,
+        "torch_dtype": "float16",
         "eos_token_id": 248044,
         "full_attention_interval": 4,
         "head_dim": 256,
         "vocab_size": 248320
     },
     "tie_word_embeddings": true,
+    "unsloth_version": "2026.4.4",
     "use_cache": false,
     "video_token_id": 248057,
     "vision_config": {
         "deepstack_visual_indexes": [],
         "depth": 24,
+        "torch_dtype": "float16",
         "hidden_act": "gelu_pytorch_tanh",
         "hidden_size": 1024,
         "in_channels": 3,

model.safetensors-00001-of-00001.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:023401fe5ec3ddf5e96ba5b8bd24338883a699cf2d0ff8bd9a3aa59a45191030
 size 4548221488

 version https://git-lfs.github.com/spec/v1
+oid sha256:ad792be39c3ce73bea7e97137d32cdab8b23ada325184758bd657ed4f7d9c995
 size 4548221488