Instructions to use Cran-May/PCB-NRSheared-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cran-May/PCB-NRSheared-2 with Transformers:

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

pipe = pipeline("text-generation", model="Cran-May/PCB-NRSheared-2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Cran-May/PCB-NRSheared-2")
model = AutoModelForCausalLM.from_pretrained("Cran-May/PCB-NRSheared-2")
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

vLLM

How to use Cran-May/PCB-NRSheared-2 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Cran-May/PCB-NRSheared-2

SGLang

How to use Cran-May/PCB-NRSheared-2 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 "Cran-May/PCB-NRSheared-2" \
    --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": "Cran-May/PCB-NRSheared-2",
		"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 "Cran-May/PCB-NRSheared-2" \
        --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": "Cran-May/PCB-NRSheared-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Cran-May/PCB-NRSheared-2 with Docker Model Runner:
```
docker model run hf.co/Cran-May/PCB-NRSheared-2
```

PCB-NRSheared-2 / README.md

Cran-May

Upload folder using huggingface_hub

b94547a verified over 1 year ago

preview code

raw

history blame contribute delete

3.09 kB

	---
	base_model:
	- AlSamCur123/Mistral-Small3-24B-InstructContinuedFine
	- trashpanda-org/MS-24B-Instruct-Mullein-v0
	- huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
	library_name: transformers
	tags:
	- mergekit
	- merge

	---
	# merge

	This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

	## Merge Details
	### Merge Method

	This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using [huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated](https://huggingface.co/huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated) as a base.

	### Models Merged

	The following models were included in the merge:
	* [AlSamCur123/Mistral-Small3-24B-InstructContinuedFine](https://huggingface.co/AlSamCur123/Mistral-Small3-24B-InstructContinuedFine)
	* [trashpanda-org/MS-24B-Instruct-Mullein-v0](https://huggingface.co/trashpanda-org/MS-24B-Instruct-Mullein-v0)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	# 文件名: pcb_della_merge_12b.yaml
	merge_method: della # 仍然使用 DELLA，因为它是一个强大的自适应剪裁方法
	base_model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
	models:
	- model: trashpanda-org/MS-24B-Instruct-Mullein-v0
	parameters:
	weight: 1.0
	# PCB策略：限制层影响范围 + 动态竞争平衡
	layers:
	- layers: "8-16"
	parameter_name: density
	value: 0.4
	- layers: "8-16"
	parameter_name: epsilon
	value: 0.15
	- layers: "8-16"
	parameter_name: lambda
	value: 1.5
	- layers: "17-24"
	parameter_name: density
	value: 0.2
	variance_threshold: 0.3

	- model: AlSamCur123/Mistral-Small3-24B-InstructContinuedFine
	parameters:
	weight: 1.0
	# 强化指令理解层
	layers:
	- layers: "0-12"
	parameter_name: density
	value: 0.7
	- layers: "0-12"
	parameter_name: epsilon
	value: 0.05
	- layers: "0-12"
	parameter_name: lambda
	value: 2.0
	variance_threshold: 0.25

	- model: huihui-ai/Mistral-Small-24B-Instruct-2501-abliterated
	parameters:
	weight: 1.0
	# 基模型参数保护策略
	density: 0.9
	layers:
	- layers: "12-24"
	parameter_name: density
	value: 1.0

	parameters:
	global_density: 0.55 # 全局剪裁密度（PCB平衡点）
	intra_balance: true
	variance_threshold: 0.2
	epsilon_range: [0.1, 0.2]

	tokenizer:
	source: base

	generation_config:
	eos_token_id: 2
	pad_token_id: 2
	repetition_penalty: 1.15
	top_k: 40
	temperature: 0.8

	# 参数压缩设置 (目标 12-13B 模型)
	architecture:
	hidden_size: 3072 # 显著降低 hidden_size (原始 5120 -> 4096 -> 3072)
	intermediate_size: 8256 # 相应调整 intermediate_size (比例保持不变)
	num_attention_heads: 24 # 相应减少 attention heads (比例保持不变)
	num_hidden_layers: 30 # 层数保持 30 层 (适度压缩)
	```