language:
- ru
- en
license: mit
library_name: transformers
tags:
- python
- code
datasets:
- MexIvanov/Vezora-Tested-22k-Python-Alpaca-ru
- MexIvanov/CodeExercise-Python-27k-ru
- zelkame/ru-stackoverflow-py
base_model: HuggingFaceH4/zephyr-7b-beta
pipeline_tag: conversational
model-index:
- name: zephyr-python-ru-merged
results:
- task:
type: text-generation
dataset:
name: gsm8k
type: gsm8k
metrics:
- type: Grade School Math 8K (5-Shot)
value: 32.52
name: Grade School Math 8K (5-Shot)
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
name: Open LLM Leaderboard
- task:
type: text-generation
dataset:
name: ai2_arc
type: ai2_arc
metrics:
- type: AI2 Reasoning Challenge (25-Shot)
value: 56.06
name: AI2 Reasoning Challenge (25-Shot)
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
name: Open LLM Leaderboard
- task:
type: text-generation
dataset:
name: HellaSwag
type: HellaSwag
metrics:
- type: HellaSwag (10-Shot)
value: 82.06
name: HellaSwag (10-Shot)
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
name: Open LLM Leaderboard
- task:
type: text-generation
dataset:
name: MMLU
type: MMLU
metrics:
- type: MMLU (5-Shot)
value: 60.02
name: MMLU (5-Shot)
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
name: Open LLM Leaderboard
- task:
type: text-generation
dataset:
name: truthfulqa
type: truthfulqa
metrics:
- type: truthfulqa:mc (0-Shot)
value: 52.81
name: truthfulqa:mc (0-Shot)
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
name: Open LLM Leaderboard
- task:
type: text-generation
dataset:
name: winogrande
type: winogrande
metrics:
- type: winogrande (5-Shot)
value: 76.95
name: winogrande (5-Shot)
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
name: Open LLM Leaderboard
- 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: 56.06
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
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: 82.06
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
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: 60.2
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
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: 52.81
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
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: 76.95
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
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: 32.52
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MexIvanov/zephyr-python-ru-merged
name: Open LLM Leaderboard
Model Card for Model ID
Model Details
Model Description
- Developed by: C.B. Pronin, A.V. Volosova, A.V. Ostroukh, Yu.N. Strogov, V.V. Kurbatov, A.S. Umarova.
- Model type: Base model HuggingFaceH4/zephyr-7b-beta merged with LoRA (Peft) adapter model MexIvanov/zephyr-python-ru trained on a mix of publicly available data and machine-translated synthetic python coding datasets.
- Language(s) (NLP): Russian, English, Python
- License: MIT
- Finetuned from model: HuggingFaceH4/zephyr-7b-beta
Model Sources
- Repository: Comming soon...
- Paper: Comming soon...
Uses
An experimental finetune of Zephyr-7b-beta, aimed at improving coding performance and support for coding-related instructions written in Russian language.
Direct Use
Instruction-based coding in Python, based of instructions written in natural language (English or Russian)
Prompt template - Zephyr:
<|system|>
</s>
<|user|>
{prompt}</s>
<|assistant|>
Bias, Risks, and Limitations
This adapter model is intended (but not limited) for research usage only. It was trained on a code based instruction set and it does not have any moderation mechanisms. Use at your own risk, we are not responsible for any usage or output of this model.
Quote from Zephyr (base-model) repository: "Zephyr-7B-β has not been aligned to human preferences for safety within the RLHF phase or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so). It is also unknown what the size and composition of the corpus was used to train the base model (mistralai/Mistral-7B-v0.1), however it is likely to have included a mix of Web data and technical sources like books and code. See the Falcon 180B model card for an example of this."
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.6.2
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: QuantizationMethod.BITS_AND_BYTES
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
Framework versions
- PEFT 0.6.2
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 60.10 |
| AI2 Reasoning Challenge (25-Shot) | 56.06 |
| HellaSwag (10-Shot) | 82.06 |
| MMLU (5-Shot) | 60.20 |
| TruthfulQA (0-shot) | 52.81 |
| Winogrande (5-shot) | 76.95 |
| GSM8k (5-shot) | 32.52 |