File size: 2,435 Bytes
f307b92 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
---
base_model:
- Theros/Qwen2.5-ColdBrew-R1
- Theros/Qwen2.5-ColdBrew-R1
- Theros/Qwen2.5-ColdBrew-R1
- Theros/Qwen2.5-ColdBrew-R1
tags:
- merge
- mergekit
- lazymergekit
- Theros/Qwen2.5-ColdBrew-R1
---
# Q2.5-ColdBrew-R1-Indigo
Q2.5-ColdBrew-R1-Indigo is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
* [Theros/Qwen2.5-ColdBrew-R1](https://huggingface.co/Theros/Qwen2.5-ColdBrew-R1)
* [Theros/Qwen2.5-ColdBrew-R1](https://huggingface.co/Theros/Qwen2.5-ColdBrew-R1)
* [Theros/Qwen2.5-ColdBrew-R1](https://huggingface.co/Theros/Qwen2.5-ColdBrew-R1)
* [Theros/Qwen2.5-ColdBrew-R1](https://huggingface.co/Theros/Qwen2.5-ColdBrew-R1)
## 🧩 Configuration
```yaml
name: Q2.5-ColdBrew-R1-Indigo
const_tag: &scale_factor 0.7071067812 # 1/sqrt(2) scaling for stability
attenuate-env: &attenuated_env
parameters:
scale:
- filter: q_proj
value: *scale_factor
- filter: k_proj
value: *scale_factor
- value: 1.0
slices:
- sources:
- model: Theros/Qwen2.5-ColdBrew-R1
layer_range: [0, 8] # Retaining foundational knowledge and language structure.
- sources:
- model: Theros/Qwen2.5-ColdBrew-R1
layer_range: [9, 19] # Full-strength duplication of mid-range reasoning layers.
- sources:
- model: Theros/Qwen2.5-ColdBrew-R1
layer_range: [10, 19] # Targeted reinforcement, slightly attenuated to avoid over-dominance.
<<: *attenuated_env
- sources:
- model: Theros/Qwen2.5-ColdBrew-R1
layer_range: [20, 28] # Keeping higher-level abstract processing untouched for stability.
merge_method: passthrough
dtype: bfloat16
normalize: true
int8_mask: true
```
## 💻 Usage
```python
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "SvalTek/Q2.5-ColdBrew-R1-Indigo"
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"])
``` |