Spaetzle-v69-7b / README.md

Update README.md

e472e2f verified 7 months ago

9.49 kB

	---
	tags:
	- merge
	- mergekit
	- lazymergekit
	language:
	- de
	- en
	base_model:
	- abideen/AlphaMonarch-dora
	- mayflowergmbh/Wiedervereinigung-7b-dpo
	- flemmingmiguel/NeuDist-Ro-7B
	- ResplendentAI/Flora_DPO_7B
	- yleo/EmertonMonarch-7B
	- occiglot/occiglot-7b-de-en-instruct
	- OpenPipe/mistral-ft-optimized-1227
	- DiscoResearch/DiscoLM_German_7b_v1
	- LeoLM/leo-mistral-hessianai-7b
	- DRXD1000/Phoenix
	- VAGOsolutions/SauerkrautLM-7b-v1-mistral
	- malteos/hermeo-7b
	- FelixChao/WestSeverus-7B-DPO-v2
	- cognitivecomputations/openchat-3.5-0106-laser
	license: cc-by-nc-4.0
	---

	# Spaetzle-v69-7b
	This is a progressive (mostly dare-ties, but also slerp) merge with the intention of a suitable compromise for English and German local tasks.

	There is also a 4q_k_m quantized [GGUF](https://huggingface.co/cstr/Spaetzle-v69-7b-GGUF).

	It should work sufficiently well with ChatML prompt template (for all merged models should have seen ChatML prompts at least in DPO stage).

	## Evaluation

	Benchmark scores are not the possible optimum, as the model attempts a compromise with a number of parameters, like German language performance, instruction following, reasoning capabilities, robustness (so far, i did not encounter inserted tokens, e.g.), model licensing, and other criteria.
	Nevertheless, they are not too bad:

	It achieves (running quantized) in
	- German EQ Bench: Score (v2_de): 62.59 (Parseable: 171.0).
	- English EQ Bench: Score (v2): 76.43 (Parseable: 171.0).

	[Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard):
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_cstr__Spaetzle-v69-7b)

	\| Metric \|Value\|
	\|---------------------------------\|----:\|
	\|Avg. \|72.87\|
	\|AI2 Reasoning Challenge (25-Shot)\|69.54\|
	\|HellaSwag (10-Shot) \|86.77\|
	\|MMLU (5-Shot) \|64.63\|
	\|TruthfulQA (0-shot) \|65.61\|
	\|Winogrande (5-shot) \|81.93\|
	\|GSM8k (5-shot) \|68.76\|

	Nous benchmark results:

	\| Model \|AGIEval\|GPT4All\|TruthfulQA\|Bigbench\|Average\|
	\|--------------------------------------------------------------\|------:\|------:\|---------:\|-------:\|------:\|
	\|[Spaetzle-v69-7b](https://huggingface.co/cstr/Spaetzle-v69-7b)\| 44.48\| 75.84\| 66.15\| 46.59\| 58.27\|

	### AGIEval
	\| Task \|Version\| Metric \|Value\| \|Stderr\|
	\|------------------------------\|------:\|--------\|----:\|---\|-----:\|
	\|agieval_aqua_rat \| 0\|acc \|25.98\|± \| 2.76\|
	\| \| \|acc_norm\|23.62\|± \| 2.67\|
	\|agieval_logiqa_en \| 0\|acc \|39.78\|± \| 1.92\|
	\| \| \|acc_norm\|39.48\|± \| 1.92\|
	\|agieval_lsat_ar \| 0\|acc \|23.48\|± \| 2.80\|
	\| \| \|acc_norm\|23.91\|± \| 2.82\|
	\|agieval_lsat_lr \| 0\|acc \|50.00\|± \| 2.22\|
	\| \| \|acc_norm\|51.76\|± \| 2.21\|
	\|agieval_lsat_rc \| 0\|acc \|63.94\|± \| 2.93\|
	\| \| \|acc_norm\|64.31\|± \| 2.93\|
	\|agieval_sat_en \| 0\|acc \|76.70\|± \| 2.95\|
	\| \| \|acc_norm\|77.67\|± \| 2.91\|
	\|agieval_sat_en_without_passage\| 0\|acc \|46.12\|± \| 3.48\|
	\| \| \|acc_norm\|44.17\|± \| 3.47\|
	\|agieval_sat_math \| 0\|acc \|34.09\|± \| 3.20\|
	\| \| \|acc_norm\|30.91\|± \| 3.12\|

	Average: 44.48%

	### GPT4All
	\| Task \|Version\| Metric \|Value\| \|Stderr\|
	\|-------------\|------:\|--------\|----:\|---\|-----:\|
	\|arc_challenge\| 0\|acc \|63.23\|± \| 1.41\|
	\| \| \|acc_norm\|64.16\|± \| 1.40\|
	\|arc_easy \| 0\|acc \|85.90\|± \| 0.71\|
	\| \| \|acc_norm\|82.49\|± \| 0.78\|
	\|boolq \| 1\|acc \|87.80\|± \| 0.57\|
	\|hellaswag \| 0\|acc \|67.05\|± \| 0.47\|
	\| \| \|acc_norm\|85.19\|± \| 0.35\|
	\|openbookqa \| 0\|acc \|38.40\|± \| 2.18\|
	\| \| \|acc_norm\|48.40\|± \| 2.24\|
	\|piqa \| 0\|acc \|82.75\|± \| 0.88\|
	\| \| \|acc_norm\|84.28\|± \| 0.85\|
	\|winogrande \| 0\|acc \|78.53\|± \| 1.15\|

	Average: 75.84%

	### TruthfulQA
	\| Task \|Version\|Metric\|Value\| \|Stderr\|
	\|-------------\|------:\|------\|----:\|---\|-----:\|
	\|truthfulqa_mc\| 1\|mc1 \|50.67\|± \| 1.75\|
	\| \| \|mc2 \|66.15\|± \| 1.48\|

	Average: 66.15%

	### Bigbench
	\| Task \|Version\| Metric \|Value\| \|Stderr\|
	\|------------------------------------------------\|------:\|---------------------\|----:\|---\|-----:\|
	\|bigbench_causal_judgement \| 0\|multiple_choice_grade\|56.84\|± \| 3.60\|
	\|bigbench_date_understanding \| 0\|multiple_choice_grade\|66.67\|± \| 2.46\|
	\|bigbench_disambiguation_qa \| 0\|multiple_choice_grade\|40.70\|± \| 3.06\|
	\|bigbench_geometric_shapes \| 0\|multiple_choice_grade\|24.79\|± \| 2.28\|
	\| \| \|exact_str_match \|10.58\|± \| 1.63\|
	\|bigbench_logical_deduction_five_objects \| 0\|multiple_choice_grade\|31.00\|± \| 2.07\|
	\|bigbench_logical_deduction_seven_objects \| 0\|multiple_choice_grade\|23.00\|± \| 1.59\|
	\|bigbench_logical_deduction_three_objects \| 0\|multiple_choice_grade\|58.00\|± \| 2.85\|
	\|bigbench_movie_recommendation \| 0\|multiple_choice_grade\|45.80\|± \| 2.23\|
	\|bigbench_navigate \| 0\|multiple_choice_grade\|52.10\|± \| 1.58\|
	\|bigbench_reasoning_about_colored_objects \| 0\|multiple_choice_grade\|69.55\|± \| 1.03\|
	\|bigbench_ruin_names \| 0\|multiple_choice_grade\|48.88\|± \| 2.36\|
	\|bigbench_salient_translation_error_detection \| 0\|multiple_choice_grade\|30.96\|± \| 1.46\|
	\|bigbench_snarks \| 0\|multiple_choice_grade\|73.48\|± \| 3.29\|
	\|bigbench_sports_understanding \| 0\|multiple_choice_grade\|74.14\|± \| 1.40\|
	\|bigbench_temporal_sequences \| 0\|multiple_choice_grade\|42.70\|± \| 1.56\|
	\|bigbench_tracking_shuffled_objects_five_objects \| 0\|multiple_choice_grade\|23.60\|± \| 1.20\|
	\|bigbench_tracking_shuffled_objects_seven_objects\| 0\|multiple_choice_grade\|18.40\|± \| 0.93\|
	\|bigbench_tracking_shuffled_objects_three_objects\| 0\|multiple_choice_grade\|58.00\|± \| 2.85\|

	Average: 46.59%

	Average score: 58.27%

	## 🧩 Merge Configuration

	Spaetzle-v69-7b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
	* [abideen/AlphaMonarch-dora](https://huggingface.co/abideen/AlphaMonarch-dora)
	* [cstr/Spaetzle-v68-7b](https://huggingface.co/cstr/Spaetzle-v68-7b)

	The merge tree in total involves the following original models:
	- [abideen/AlphaMonarch-dora](https://huggingface.co/abideen/AlphaMonarch-dora)
	- [mayflowergmbh/Wiedervereinigung-7b-dpo](https://huggingface.co/mayflowergmbh/Wiedervereinigung-7b-dpo)
	- [flemmingmiguel/NeuDist-Ro-7B](https://huggingface.co/flemmingmiguel/NeuDist-Ro-7B)
	- [ResplendentAI/Flora_DPO_7B](https://huggingface.co/ResplendentAI/Flora_DPO_7B)
	- [yleo/EmertonMonarch-7B](https://huggingface.co/yleo/EmertonMonarch-7B)
	- [occiglot/occiglot-7b-de-en-instruct](https://huggingface.co/occiglot/occiglot-7b-de-en-instruct)
	- [OpenPipe/mistral-ft-optimized-1227](https://huggingface.co/OpenPipe/mistral-ft-optimized-1227)
	- [DiscoResearch/DiscoLM_German_7b_v1](https://huggingface.co/DiscoResearch/DiscoLM_German_7b_v1)
	- [LeoLM/leo-mistral-hessianai-7b](https://huggingface.co/LeoLM/leo-mistral-hessianai-7b)
	- [DRXD1000/Phoenix](https://huggingface.co/DRXD1000/Phoenix)
	- [VAGOsolutions/SauerkrautLM-7b-v1-mistral](https://huggingface.co/VAGOsolutions/SauerkrautLM-7b-v1-mistral)
	- [malteos/hermeo-7b](https://huggingface.co/malteos/hermeo-7b)
	- [FelixChao/WestSeverus-7B-DPO-v2](https://huggingface.co/FelixChao/WestSeverus-7B-DPO-v2)
	- [cognitivecomputations/openchat-3.5-0106-laser](https://huggingface.co/cognitivecomputations/openchat-3.5-0106-laser)

	For this last merge:

	```yaml
	models:
	- model: cstr/Spaetzle-v68-7b
	# no parameters necessary for base model
	- model: abideen/AlphaMonarch-dora
	parameters:
	density: 0.60
	weight: 0.30
	merge_method: dare_ties
	base_model: cstr/Spaetzle-v68-7b
	parameters:
	int8_mask: true
	dtype: bfloat16
	random_seed: 0
	tokenizer_source: base
	```

	## 💻 Usage

	```python
	!pip install -qU transformers accelerate

	from transformers import AutoTokenizer
	import transformers
	import torch

	model = "cstr/Spaetzle-v69-7b"
	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"])
	```