Quantization made by Richard Erkhov.
StrangeMerges_8-7B-slerp - GGUF
- Model creator: https://huggingface.co/Gille/
- Original model: https://huggingface.co/Gille/StrangeMerges_8-7B-slerp/
Original model description:
license: apache-2.0 tags: - merge - mergekit - lazymergekit - Gille/StrangeMerges_7-7B-slerp - Gille/StrangeMerges_5-7B-ties base_model: - Gille/StrangeMerges_7-7B-slerp - Gille/StrangeMerges_5-7B-ties model-index: - name: StrangeMerges_8-7B-slerp results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 71.08 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_8-7B-slerp name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 87.75 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_8-7B-slerp name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 65.26 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_8-7B-slerp name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 64.52 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_8-7B-slerp name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 84.45 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_8-7B-slerp name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 67.25 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Gille/StrangeMerges_8-7B-slerp name: Open LLM Leaderboard
StrangeMerges_8-7B-slerp
StrangeMerges_8-7B-slerp is a merge of the following models using LazyMergekit:
🧩 Configuration
slices:
- sources:
- model: Gille/StrangeMerges_7-7B-slerp
layer_range: [0, 32]
- model: Gille/StrangeMerges_5-7B-ties
layer_range: [0, 32]
merge_method: slerp
base_model: Gille/StrangeMerges_7-7B-slerp
parameters:
t:
- filter: self_attn
value: [0.9, 0.5, 0.3, 0.7, 0.1]
- filter: mlp
value: [0.1, 0.5, 0.7, 0.3, 0.9]
- value: 0.5
dtype: bfloat16
💻 Usage
!pip install -qU transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "Gille/StrangeMerges_8-7B-slerp"
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"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 73.39 |
AI2 Reasoning Challenge (25-Shot) | 71.08 |
HellaSwag (10-Shot) | 87.75 |
MMLU (5-Shot) | 65.26 |
TruthfulQA (0-shot) | 64.52 |
Winogrande (5-shot) | 84.45 |
GSM8k (5-shot) | 67.25 |