Views
No views yet
1base_model: kyujinpy/Sakura-SOLAR-Instruct
2gate_mode: hidden
3experts:
4 - source_model: kyujinpy/Sakura-SOLAR-Instruct
5 positive_prompts:
6 - "chat"
7 - "assistant"
8 - "tell me"
9 - "explain"
10 negative_prompts:
11 - "mathematics"
12 - "reasoning"
13 - source_model: jeonsworld/CarbonVillain-en-10.7B-v1
14 positive_prompts:
15 - "write"
16 - "AI"
17 - "text"
18 - "paragraph"
19 negative_prompts:
20 - "mathematics"
21 - "reasoning"
22 - source_model: rishiraj/meow
23 positive_prompts:
24 - "chat"
25 - "say"
26 - "what"
27 negative_prompts:
28 - "mathematics"
29 - "reasoning"
30 - source_model: kyujinpy/Sakura-SOLRCA-Math-Instruct-DPO-v2
31 positive_prompts:
32 - "reason"
33 - "math"
34 - "mathematics"
35 - "solve"
36 - "count"
37 negative_prompts:
38 - "chat"
39 - "assistant"
40 - "storywriting"1!pip install -qU transformers bitsandbytes accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "mlabonne/Mixolar-4x7b"
8
9tokenizer = AutoTokenizer.from_pretrained(model)
10pipeline = transformers.pipeline(
11 "text-generation",
12 model=model,
13 model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
14)
15
16messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
17prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
18outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
19print(outputs[0]["generated_text"])| Metric | Value |
|---|---|
| Avg. | 74.18 |
| AI2 Reasoning Challenge (25-Shot) | 71.08 |
| HellaSwag (10-Shot) | 88.44 |
| MMLU (5-Shot) | 66.29 |
| TruthfulQA (0-shot) | 71.81 |
| Winogrande (5-shot) | 83.58 |
| GSM8k (5-shot) | 63.91 |