294 lines
6.6 KiB
Markdown
294 lines
6.6 KiB
Markdown
|
---
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
license: other
|
||
|
|
tags:
|
||
|
|
- axolotl
|
||
|
|
- instruct
|
||
|
|
- finetune
|
||
|
|
- chatml
|
||
|
|
- gpt4
|
||
|
|
- synthetic data
|
||
|
|
- science
|
||
|
|
- physics
|
||
|
|
- chemistry
|
||
|
|
- biology
|
||
|
|
- math
|
||
|
|
- qwen
|
||
|
|
- qwen2
|
||
|
|
base_model: Weyaxi/Einstein-v7-Qwen2-7B
|
||
|
|
datasets:
|
||
|
|
- allenai/ai2_arc
|
||
|
|
- camel-ai/physics
|
||
|
|
- camel-ai/chemistry
|
||
|
|
- camel-ai/biology
|
||
|
|
- camel-ai/math
|
||
|
|
- metaeval/reclor
|
||
|
|
- openbookqa
|
||
|
|
- mandyyyyii/scibench
|
||
|
|
- derek-thomas/ScienceQA
|
||
|
|
- TIGER-Lab/ScienceEval
|
||
|
|
- jondurbin/airoboros-3.2
|
||
|
|
- LDJnr/Capybara
|
||
|
|
- Cot-Alpaca-GPT4-From-OpenHermes-2.5
|
||
|
|
- STEM-AI-mtl/Electrical-engineering
|
||
|
|
- knowrohit07/saraswati-stem
|
||
|
|
- sablo/oasst2_curated
|
||
|
|
- lmsys/lmsys-chat-1m
|
||
|
|
- TIGER-Lab/MathInstruct
|
||
|
|
- bigbio/med_qa
|
||
|
|
- meta-math/MetaMathQA-40K
|
||
|
|
- openbookqa
|
||
|
|
- piqa
|
||
|
|
- metaeval/reclor
|
||
|
|
- derek-thomas/ScienceQA
|
||
|
|
- scibench
|
||
|
|
- sciq
|
||
|
|
- Open-Orca/SlimOrca
|
||
|
|
- migtissera/Synthia-v1.3
|
||
|
|
- TIGER-Lab/ScienceEval
|
||
|
|
- allenai/WildChat
|
||
|
|
- microsoft/orca-math-word-problems-200k
|
||
|
|
- openchat/openchat_sharegpt4_dataset
|
||
|
|
- teknium/GPTeacher-General-Instruct
|
||
|
|
- m-a-p/CodeFeedback-Filtered-Instruction
|
||
|
|
- totally-not-an-llm/EverythingLM-data-V3
|
||
|
|
- HuggingFaceH4/no_robots
|
||
|
|
- OpenAssistant/oasst_top1_2023-08-25
|
||
|
|
- WizardLM/WizardLM_evol_instruct_70k
|
||
|
|
- abacusai/SystemChat-1.1
|
||
|
|
- H-D-T/Buzz-V1.2
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
---
|
||
|
|
|
||
|
|
# 🔬 Einstein-v7-Qwen2-7B-GGUF
|
||
|
|
This is quantized version of [Weyaxi/Einstein-v7-Qwen2-7B](https://huggingface.co/Weyaxi/Einstein-v7-Qwen2-7B) created using llama.cpp
|
||
|
|
|
||
|
|
# Model Description
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
This model is a full fine-tuned version of [Qwen/Qwen2-7B](https://huggingface.co/Qwen/Qwen2-7B) on diverse datasets.
|
||
|
|
|
||
|
|
This model is finetuned using `8xMI300X` using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
|
||
|
|
|
||
|
|
<details><summary>See axolotl config</summary>
|
||
|
|
|
||
|
|
axolotl version: `0.4.0`
|
||
|
|
```yaml
|
||
|
|
base_model: Qwen/Qwen2-7B
|
||
|
|
model_type: AutoModelForCausalLM
|
||
|
|
tokenizer_type: AutoTokenizer
|
||
|
|
|
||
|
|
load_in_8bit: false
|
||
|
|
load_in_4bit: false
|
||
|
|
strict: false
|
||
|
|
|
||
|
|
chat_template: chatml
|
||
|
|
datasets:
|
||
|
|
- path: data/airoboros_3.2_without_contextual_slimorca_orca_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/allenai_wild_chat_gpt4_english_toxic_random_half_4k_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
strict: false
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/buzz_unstacked_chosen_math_removed_filtered.json
|
||
|
|
ds_type: json
|
||
|
|
type: alpaca
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/capybara_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/everythinglm-data-v3_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
strict: false
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/gpt4_data_lmys_1m_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/gpteacher-instruct-special-alpaca.json
|
||
|
|
ds_type: json
|
||
|
|
type: gpteacher
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/merged_all.json
|
||
|
|
ds_type: json
|
||
|
|
type: alpaca
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/no_robots_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
strict: false
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/oasst_top1_from_fusechatmixture_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
strict: false
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/pippa_bagel_repo_3k_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/rpguild_quarter_alignment_lab_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/sharegpt_gpt4_english.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/slimorca_dedup_filtered_95k_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/soda_diaolog_longest_tenth_buzz_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/synthia-v1.3_sharegpt_12500.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
- path: data/system_conversations_dolphin_sharegpt.json
|
||
|
|
ds_type: json
|
||
|
|
type: sharegpt
|
||
|
|
conversation: chatml
|
||
|
|
|
||
|
|
dataset_prepared_path: last_run_prepared
|
||
|
|
val_set_size: 0.002
|
||
|
|
|
||
|
|
output_dir: ./Einstein-v7-Qwen2-7B-model
|
||
|
|
|
||
|
|
sequence_len: 8192
|
||
|
|
sample_packing: true
|
||
|
|
pad_to_sequence_len: true
|
||
|
|
eval_sample_packing: false
|
||
|
|
|
||
|
|
wandb_project: Einstein
|
||
|
|
wandb_entity:
|
||
|
|
wandb_watch:
|
||
|
|
wandb_name:
|
||
|
|
wandb_log_model:
|
||
|
|
hub_model_id: Weyaxi/Einstein-v7-Qwen2-7B
|
||
|
|
|
||
|
|
gradient_accumulation_steps: 4
|
||
|
|
micro_batch_size: 6
|
||
|
|
num_epochs: 2
|
||
|
|
optimizer: paged_adamw_8bit
|
||
|
|
lr_scheduler: cosine
|
||
|
|
learning_rate: 0.00001 # look
|
||
|
|
|
||
|
|
train_on_inputs: false
|
||
|
|
group_by_length: false
|
||
|
|
bf16: auto
|
||
|
|
fp16:
|
||
|
|
tf32: false
|
||
|
|
|
||
|
|
gradient_checkpointing: unsloth
|
||
|
|
gradient_checkpointing_kwargs:
|
||
|
|
use_reentrant: true # look
|
||
|
|
early_stopping_patience:
|
||
|
|
resume_from_checkpoint:
|
||
|
|
local_rank:
|
||
|
|
logging_steps: 1
|
||
|
|
xformers_attention:
|
||
|
|
flash_attention: true
|
||
|
|
|
||
|
|
warmup_steps: 10
|
||
|
|
evals_per_epoch: 2
|
||
|
|
eval_table_size:
|
||
|
|
eval_max_new_tokens: 128
|
||
|
|
saves_per_epoch: 1
|
||
|
|
debug:
|
||
|
|
|
||
|
|
deepspeed: deepspeed_configs/zero3_bf16.json
|
||
|
|
weight_decay: 0.05
|
||
|
|
fsdp:
|
||
|
|
fsdp_config:
|
||
|
|
special_tokens:
|
||
|
|
eos_token: "<|im_end|>"
|
||
|
|
pad_token: "<|end_of_text|>"
|
||
|
|
tokens:
|
||
|
|
- "<|im_start|>"
|
||
|
|
- "<|im_end|>"
|
||
|
|
```
|
||
|
|
|
||
|
|
</details><br>
|
||
|
|
|
||
|
|
# 💬 Prompt Template
|
||
|
|
|
||
|
|
You can use ChatML prompt template while using the model:
|
||
|
|
|
||
|
|
### ChatML
|
||
|
|
|
||
|
|
```
|
||
|
|
<|im_start|>system
|
||
|
|
{system}<|im_end|>
|
||
|
|
<|im_start|>user
|
||
|
|
{user}<|im_end|>
|
||
|
|
<|im_start|>assistant
|
||
|
|
{asistant}<|im_end|>
|
||
|
|
```
|
||
|
|
|
||
|
|
This prompt template is available as a [chat template](https://huggingface.co/docs/transformers/main/chat_templating), which means you can format messages using the
|
||
|
|
`tokenizer.apply_chat_template()` method:
|
||
|
|
|
||
|
|
```python
|
||
|
|
messages = [
|
||
|
|
{"role": "system", "content": "You are helpful AI asistant."},
|
||
|
|
{"role": "user", "content": "Hello!"}
|
||
|
|
]
|
||
|
|
gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
|
||
|
|
model.generate(**gen_input)
|
||
|
|
```
|
||
|
|
|
||
|
|
# 📊 Datasets used in this model
|
||
|
|
|
||
|
|
The datasets used to train this model are listed in the metadata section of the model card.
|
||
|
|
|
||
|
|
Please note that certain datasets mentioned in the metadata may have undergone filtering based on various criteria.
|
||
|
|
|
||
|
|
The results of this filtering process and its outcomes are in a diffrent repository:
|
||
|
|
|
||
|
|
[Weyaxi/sci-datasets/main](https://huggingface.co/datasets/Weyaxi/sci-datasets/tree/main)
|
||
|
|
|
||
|
|
|
||
|
|
# 🎯 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||
|
|
|
||
|
|
# 🤖 Additional information about training
|
||
|
|
|
||
|
|
This model is full fine-tuned for 2 epoch.
|
||
|
|
|
||
|
|
Total number of steps was 500.
|
||
|
|
|
||
|
|
<details><summary>Loss graph</summary>
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
</details><br>
|