Views
No views yet
1models:
2 - model: CultriX/MonaTrix-v4
3 # No parameters necessary for base model
4 - model: eren23/ogno-monarch-jaskier-merge-7b-v2
5 parameters:
6 weight: 0.7
7 density: 0.6
8 - model: Gille/StrangeMerges_25-7B-dare_ties
9 parameters:
10 weight: 0.3
11 density: 0.45
12merge_method: dare_ties
13base_model: CultriX/MonaTrix-v4
14parameters:
15 int8_mask: true
16dtype: bfloat161!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "Gille/StrangeMerges_28-7B-dare_ties"
8messages = [{"role": "user", "content": "What is a large language model?"}]
9
10tokenizer = AutoTokenizer.from_pretrained(model)
11prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
12pipeline = transformers.pipeline(
13 "text-generation",
14 model=model,
15 torch_dtype=torch.float16,
16 device_map="auto",
17)
18
19outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
20print(outputs[0]["generated_text"])| Metric | Value |
|---|---|
| Avg. | 75.86 |
| AI2 Reasoning Challenge (25-Shot) | 72.18 |
| HellaSwag (10-Shot) | 89.08 |
| MMLU (5-Shot) | 64.68 |
| TruthfulQA (0-shot) | 77.55 |
| Winogrande (5-shot) | 83.50 |
| GSM8k (5-shot) | 68.16 |