Quantization made by Richard Erkhov.

Github

Discord

Request more models

Rain-7B-v0.1 - GGUF

• Model creator: https://huggingface.co/raincandy-u/
• Original model: https://huggingface.co/raincandy-u/Rain-7B-v0.1/

Name	Quant method	Size
Rain-7B-v0.1.Q2_K.gguf	Q2_K	2.89GB
Rain-7B-v0.1.IQ3_XS.gguf	IQ3_XS	3.18GB
Rain-7B-v0.1.IQ3_S.gguf	IQ3_S	3.32GB
Rain-7B-v0.1.Q3_K_S.gguf	Q3_K_S	3.32GB
Rain-7B-v0.1.IQ3_M.gguf	IQ3_M	3.48GB
Rain-7B-v0.1.Q3_K.gguf	Q3_K	3.65GB
Rain-7B-v0.1.Q3_K_M.gguf	Q3_K_M	3.65GB
Rain-7B-v0.1.Q3_K_L.gguf	Q3_K_L	3.93GB
Rain-7B-v0.1.IQ4_XS.gguf	IQ4_XS	4.02GB
Rain-7B-v0.1.Q4_0.gguf	Q4_0	4.2GB
Rain-7B-v0.1.IQ4_NL.gguf	IQ4_NL	4.22GB
Rain-7B-v0.1.Q4_K_S.gguf	Q4_K_S	4.23GB
Rain-7B-v0.1.Q4_K.gguf	Q4_K	4.44GB
Rain-7B-v0.1.Q4_K_M.gguf	Q4_K_M	4.44GB
Rain-7B-v0.1.Q4_1.gguf	Q4_1	4.62GB
Rain-7B-v0.1.Q5_0.gguf	Q5_0	5.03GB
Rain-7B-v0.1.Q5_K_S.gguf	Q5_K_S	5.03GB
Rain-7B-v0.1.Q5_K.gguf	Q5_K	5.15GB
Rain-7B-v0.1.Q5_K_M.gguf	Q5_K_M	5.15GB
Rain-7B-v0.1.Q5_1.gguf	Q5_1	5.44GB
Rain-7B-v0.1.Q6_K.gguf	Q6_K	5.91GB
Rain-7B-v0.1.Q8_0.gguf	Q8_0	7.65GB

Original model description:

license: other license_name: tongyi-qianwen license_link: https://huggingface.co/Qwen/Qwen1.5-7B-Chat/raw/main/LICENSE datasets:

• yys/OpenOrca-Chinese language:
• zh
• en pipeline_tag: text-generation tags:
• CoT

---

<style> @font-face { font-family: Zpix; src: url(https://zpix.now.sh/zpix.woff2?v2021-03-21); } * { font-family:Zpix; } #main-ame-back { font-family:Zpix; color: #fd96fd !important; padding: 15px; } a { color:#fd87c2 !important } #main-ame-back h1{ color:#8e45f5 !important; } </style>

ジェルばんは~

🧬UPDATE: Please see Here for v0.2 model.

🧬Rain-7B-v0.1

Rain-7B-v0.1 is an experimental model finetuned on Qwen1.5-7B-Chat with thousands of chain of thought conversations.

It work better for "think step by step" prompt.

🧬Evaluation

Model name	MMLU
Qwen1.5-7B-Chat	55.8
Rain-7B-v0.1	58.1

🧬Usage

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "raincandy-u/Rain-7B-v0.1"
messages = [{"role": "user", "content": "What is chain of thoughts?"}]

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"])