Downloads · 30 days
0
Mistral-7B-Evol-Instruct-Chinese
s3nh/Mistral-7B-Evol-Instruct-Chinese
Mistral-7B-Evol-Instruct-Chinese is a text generation model from s3nh. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Access
Public
Updated Dec 28, 2023
Parameters
7.2B
14.5 GB on disk
Likes
6
Public
Repo makeup
Click a slice to open those files.
.safetensors14.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Model type
- mistral
- Access
- Public
- Created
- Dec 28, 2023
- Updated
- Dec 28, 2023
- SHA
- 6bd66b51
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
mistral-instruct
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the FreedomIntelligence/Evol-Instruct-Chinese-GPT4 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9519
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0002
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0979 | 0.0 | 1 | 1.0964 |
| 0.9735 | 0.25 | 82 | 0.9782 |
| 0.9577 | 0.5 | 164 | 0.9619 |
| 0.9281 | 0.75 | 246 | 0.9536 |
| 0.8988 | 1.0 | 328 | 0.9519 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0
Training procedure
The following bitsandbytes quantization config was used during training:
- quant_method: bitsandbytes
- 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: True
- bnb_4bit_compute_dtype: bfloat16
Framework versions
- PEFT 0.6.0
- Task
- Text Generation
- Library
- peft
- Type
- mistral
- License
- apache-2.0
- Languages
- zh, en
- Created
- Dec 28, 2023
- Updated
- Dec 28, 2023