Instructions to use YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c with Transformers:

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

pipe = pipeline("image-text-to-text", model="YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c")
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("YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c")
model = AutoModelForMultimodalLM.from_pretrained("YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c", 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=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c",
		"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/YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c

SGLang

How to use YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c 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 "YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c" \
    --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": "YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c",
		"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 "YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c" \
        --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": "YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c",
		"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 YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c with Docker Model Runner:
```
docker model run hf.co/YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c
```

Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c

基于 Qwen/Qwen3.8-27B 的单阶段 della_linear 融合,四个源同时入场。

配方

base_model: Qwen/Qwen3.8-27B
merge_method: della_linear
dtype: bfloat16
tokenizer:
  source: base
parameters:
  int8_mask: true
  normalize: true
  lambda: 1.0
models:
  - model: kai-os/Carnice-V3
    parameters:
      weight: 0.54
      density: 0.99
      epsilon: 0.08
  - model: etemiz/Ostrich-27B-Qwen3.8-260815
    parameters:
      weight: 0.004
      density: 0.5
      epsilon: 0.32
  - model: vectionlabs/Salience-27B-R5
    parameters:
      weight: 0.3
      density: 0.6
      epsilon: 0.32
  - model: YFC-112358/Qwen3.8-27B-TM-Gemma4-Glimmer-v3
    parameters:
      weight: 0.65
      density: 0.99
      epsilon: 0.08

实测读数

源	weight	density	epsilon	名义占比	实测占比
`kai-os/Carnice-V3`	0.54	0.99	0.08	36.1%	3.9%
`etemiz/Ostrich-27B-Qwen3.8-260815`	0.004	0.5	0.32	0.3%	48.8%
`vectionlabs/Salience-27B-R5`	0.3	0.6	0.32	20.1%	17.2%
`YFC-112358/Qwen3.8-27B-TM-Gemma4-Glimmer-v3`	0.65	0.99	0.08	43.5%	0.0%

振幅 ‖λ·δ_mix‖ / ‖base‖ 中位数:0.0006（全量构建）
合并张量 866 张 / 原样搬运 333 张（共 1199 张）
随机种子 20260827,按张量名 + 行区间氾生 ⇒ 断点续传逐位可重现

口径说明（重要）

normalize: true ⇒ 每张张量的增量除以当场源的权重之和（四源齐全时 Σw = 1.494）。所以名义 weight 只決定相对比例,不決定绝对强度。
磁幅剪枝（magnitude pruning）在行块内排序,不是整张张量全局排序——这是流式合并的必然近似,存活率期望仍等于 density。
剪完的存活项除以入选概率做无偏重标（rescale）,所以 density 降低时幅度会被放大 ≈ 1/√d。
计算全程 fp32,落盘 bf16。
int8_mask: true 在本实现里是空操作（它只是 mergekit 的显存优化开关,不改变数值）。
della_linear 不做符号选举,所以不存在“少数源被多数源否决”这回事;剪完直接加权相加。想要符号选举把 Cell 1 的 CONSENSUS 改成 True。
tokenizer / config 全部取自 Qwen/Qwen3.8-27B（tokenizer.source = base）,四个源自己加的 special token 不会进来。

使用

from transformers import AutoModelForCausalLM, AutoTokenizer
m = AutoModelForCausalLM.from_pretrained("YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c", torch_dtype="bfloat16", device_map="auto")
tk = AutoTokenizer.from_pretrained("YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c")

由 Qwen38_v5_della_linear.ipynb 逐张量流式构建（单机、不落全量磁盘）。

Downloads last month: 111

Safetensors

Model size

28B params

Tensor type

BF16

Model tree for YFC-112358/Qwen3.8-27B-Della-Carnice-Ostrich-Salience-Glimmer-v5c

Qwen/Qwen3.8-27B

YFC-112358/Qwen3.8-27B-TM-Gemma4-Glimmer-v3

etemiz/Ostrich-27B-Qwen3.8-260815

kai-os/Carnice-V3

vectionlabs/Salience-27B-R5

Merge model

this model

Adapters

1 model