Weyaxi / Einstein-7B

huggingface.co
Total runs: 12
24-hour runs: 1
7-day runs: 0
30-day runs: 4
Model's Last Updated: January 28 2024
text-generation

Introduction of Einstein-7B

Model Details of Einstein-7B

image/jpeg

🔬 Einstein-7B

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on datasets related to science.

This model is fine-tuned using QLoRa and axolotl .

This model's training was sponsored by sablo.ai .

See axolotl config

axolotl version: 0.3.0

base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true

load_in_8bit: false
load_in_4bit: true
strict: false

datasets:
  - path: sci-datasets/arc_challange_train_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/camelai_biology_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/camelai_chemistry_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/camelai_physics_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/openbookqa_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/reclor_science_alpaca.json
    ds_type: json
    type: alpaca
    
  - path: sci-datasets/scibench_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/scienceqa_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/theoremqa_alpaca.json
    ds_type: json
    type: alpaca

  - path: sci-datasets/tiger_scienceeval_alpaca.json
    ds_type: json
    type: alpaca

dataset_prepared_path: last_run_prepared
val_set_size: 0
output_dir: ./science-mistral

adapter: qlora
lora_model_dir:

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

lora_r: 128
lora_alpha: 64
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

wandb_project: huggingface
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
hub_model_id: Weyaxi/science-mistral

# change #
gradient_accumulation_steps: 12
micro_batch_size: 6
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
# change #

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10


saves_per_epoch: 3
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

📊 Datasets

Following datasets were used in this model:

💬 Prompt Template

You can use this prompt template while using the model:

Alpaca
Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
{instruction}

### Input:
{input}

### Response:

🤝 Acknowledgments

Thanks to Platypus for providing scripts to convert some of the datasets to Alpaca format: Platypus/data_pipeline

Thanks to all the dataset authors mentioned in the datasets section.

Thanks to axolotl for making the repository I used to make this model.

Built with Axolotl

If you would like to support me:

☕ Buy Me a Coffee

Runs of Weyaxi Einstein-7B on huggingface.co

12
Total runs
1
24-hour runs
1
3-day runs
0
7-day runs
4
30-day runs

More Information About Einstein-7B huggingface.co Model

More Einstein-7B license Visit here:

https://choosealicense.com/licenses/other

Einstein-7B huggingface.co

Einstein-7B huggingface.co is an AI model on huggingface.co that provides Einstein-7B's model effect (), which can be used instantly with this Weyaxi Einstein-7B model. huggingface.co supports a free trial of the Einstein-7B model, and also provides paid use of the Einstein-7B. Support call Einstein-7B model through api, including Node.js, Python, http.

Einstein-7B huggingface.co Url

https://huggingface.co/Weyaxi/Einstein-7B

Weyaxi Einstein-7B online free

Einstein-7B huggingface.co is an online trial and call api platform, which integrates Einstein-7B's modeling effects, including api services, and provides a free online trial of Einstein-7B, you can try Einstein-7B online for free by clicking the link below.

Weyaxi Einstein-7B online free url in huggingface.co:

https://huggingface.co/Weyaxi/Einstein-7B

Einstein-7B install

Einstein-7B is an open source model from GitHub that offers a free installation service, and any user can find Einstein-7B on GitHub to install. At the same time, huggingface.co provides the effect of Einstein-7B install, users can directly use Einstein-7B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Einstein-7B install url in huggingface.co:

https://huggingface.co/Weyaxi/Einstein-7B

Url of Einstein-7B

Einstein-7B huggingface.co Url

Provider of Einstein-7B huggingface.co

Weyaxi
ORGANIZATIONS

Other API from Weyaxi

huggingface.co

Total runs: 888
Run Growth: -126
Growth Rate: -14.19%
Updated:January 28 2024
huggingface.co

Total runs: 294
Run Growth: -427
Growth Rate: -135.99%
Updated:January 17 2024
huggingface.co

Total runs: 264
Run Growth: -458
Growth Rate: -159.58%
Updated:January 15 2024
huggingface.co

Total runs: 264
Run Growth: -463
Growth Rate: -163.03%
Updated:January 17 2024
huggingface.co

Total runs: 24
Run Growth: -28
Growth Rate: -116.67%
Updated:February 02 2024
huggingface.co

Total runs: 17
Run Growth: 12
Growth Rate: 70.59%
Updated:June 24 2024
huggingface.co

Total runs: 6
Run Growth: -2
Growth Rate: -33.33%
Updated:November 26 2023