---
title: NeuralStock-7B
canonical_url: "https://www.modelscope.cn/models/Kukedlc/NeuralStock-7B"
md_url: "https://www.modelscope.cn/models/Kukedlc/NeuralStock-7B.md"
repository: Kukedlc/NeuralStock-7B
last_updated: 2026-06-01
model_type:
  - mistral
architectures:
  - MistralForCausalLM
base_model:
  - liminerity/M7-7b
  - Gille/StrangeMerges_32-7B-slerp
  - automerger/YamShadow-7B
base_model_relation: merge
parameters: 7.2B
tensor_type:
  - BF16
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 15
stars: 0
tags:
  - merge
  - mergekit
  - lazymergekit
  - liminerity/M7-7b
  - Gille/StrangeMerges_32-7B-slerp
  - automerger/YamShadow-7B
---

# NeuralStock-7B

> NeuralStock-7B - Kukedlc 在 ModelScope 开源的模型。NeuralStock-7B is a merge of the following models using LazyMergekit: liminerity/M7-7b Gille/StrangeMerges32-7B-slerp automerger/YamShadow-7B

Kukedlc/NeuralStock-7B 是 ModelScope 魔搭社区上的 7.2B 参数机器学习模型，基于 liminerity/M7-7b、Gille/StrangeMerges_32-7B-slerp、automerger/YamShadow-7B 构建。

- **Repository**: Kukedlc/NeuralStock-7B
- **Parameters**: 7.2B
- **Base model**: liminerity/M7-7b, Gille/StrangeMerges_32-7B-slerp, automerger/YamShadow-7B
- **Tags**: merge, mergekit, lazymergekit, liminerity/M7-7b, Gille/StrangeMerges_32-7B-slerp, automerger/YamShadow-7B
- **Downloads**: 15
- **Stars**: 0
- **Last updated**: 2026-06-01

Source: https://www.modelscope.cn/models/Kukedlc/NeuralStock-7B

---

# NeuralStock-7B

NeuralStock-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [liminerity/M7-7b](https://huggingface.co/liminerity/M7-7b)
* [Gille/StrangeMerges_32-7B-slerp](https://huggingface.co/Gille/StrangeMerges_32-7B-slerp)
* [automerger/YamShadow-7B](https://huggingface.co/automerger/YamShadow-7B)

## 🧩 Configuration

```yaml
slices:
  - sources:
      - model: liminerity/M7-7b
        layer_range: [0, 32]
      - model: Gille/StrangeMerges_32-7B-slerp
        layer_range: [0, 32]
      - model: automerger/YamShadow-7B
        layer_range: [0, 32]
merge_method: model_stock
base_model: liminerity/M7-7b
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16
```

## 💻 Usage

```python
!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Kukedlc/NeuralStock-7B"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
```