Views
No views yet
1models:
2 - model: Kukedlc/NeuralSirKrishna-7b
3 # No parameters necessary for base model
4 - model: WizardLM/WizardMath-7B-V1.1
5 parameters:
6 density: 0.66
7 weight: 0.2
8 - model: mlabonne/NeuralDaredevil-7B
9 parameters:
10 density: 0.55
11 weight: 0.2
12 - model: Kukedlc/Neural4gsm8k
13 parameters:
14 density: 0.55
15 weight: 0.2
16 - model: Eric111/Mayo
17 parameters:
18 density: 0.44
19 weight: 0.2
20 - model: Kukedlc/NeuralSirKrishna-7b
21 parameters:
22 density: 0.66
23 weight: 0.2
24merge_method: dare_ties
25base_model: Kukedlc/NeuralSirKrishna-7b
26parameters:
27 int8_mask: true
28dtype: bfloat16
1!pip install -qU transformers accelerate
2
3from transformers import AutoTokenizer
4import transformers
5import torch
6
7model = "Kukedlc/NeuralMaths-Experiment-7b"
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. | 73.95 |
| AI2 Reasoning Challenge (25-Shot) | 69.71 |
| HellaSwag (10-Shot) | 87.48 |
| MMLU (5-Shot) | 65.01 |
| TruthfulQA (0-shot) | 63.83 |
| Winogrande (5-shot) | 82.48 |
| GSM8k (5-shot) | 75.21 |