---
language:
- en
license: other
tags:
- axolotl
- generated_from_trainer
- instruct
- finetune
- chatml
- gpt4
- synthetic data
- science
- physics
- chemistry
- biology
- math
- llama
- llama3
base_model: meta-llama/Meta-Llama-3-8B
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
model-index:
- name: Einstein-v6.1-Llama3-8B
results:
- 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: 62.46
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
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: 82.41
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
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: 66.19
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
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: 55.1
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
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: 79.32
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
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: 66.11
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Weyaxi/Einstein-v6.1-Llama3-8B
name: Open LLM Leaderboard
---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/5s12oq859qLfDkkTNam_C.png)
# 🔬 Einstein-v6.1-Llama3-8B
This model is a full fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/Einstein-v6.1-Llama3-8) on diverse datasets.
This model is finetuned using `8xRTX3090` + `1xRTXA6000` using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl).
This model's training was sponsored by [sablo.ai](https://sablo.ai).
See axolotl config
axolotl version: `0.4.0`
```yaml
base_model: meta-llama/Meta-Llama-3-8B
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer
load_in_8bit: false
load_in_4bit: false
strict: false
chat_template: chatml
datasets:
- path: data/merged_all.json
ds_type: json
type: alpaca
conversation: chatml
- path: data/gpteacher-instruct-special-alpaca.json
ds_type: json
type: gpteacher
conversation: chatml
- path: data/wizardlm_evol_instruct_70k_random_half.json
ds_type: json
type: alpaca
conversation: chatml
- path: data/capybara_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/cot_alpaca_gpt4_extracted_openhermes_2.5_sharegpt.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/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/pippa_bagel_repo_3k_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/gpt4_data_lmys_1m_sharegpt.json
ds_type: json
type: sharegpt
conversation: chatml
- path: data/sharegpt_gpt4_english.json
ds_type: json
type: sharegpt
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/everythinglm-data-v3_sharegpt.json
ds_type: json
type: sharegpt
strict: false
conversation: chatml
dataset_prepared_path: last_run_prepared
val_set_size: 0.002
output_dir: ./Einstein-v6.1-Llama3-8B-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: Einstein-v6.1-Llama3-2-epoch
wandb_log_model:
hub_model_id: Weyaxi/Einstein-v6.1-Llama3-8B
save_safetensors: true
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit # look
lr_scheduler: cosine
learning_rate: 0.000005 # look
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
evals_per_epoch: 2
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 2
debug:
deepspeed: zero3_bf16_cpuoffload_params.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: ""
eos_token: "<|im_end|>"
unk_token: ""
pad_token: <|end_of_text|> # changed
tokens:
- "<|im_start|>"
```
# 💬 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 details of this filtering process and its outcomes are documented in the `data` folder of this repository:
[Weyaxi/Einstein-v6.1-Llama3-8B/data](https://huggingface.co/Weyaxi/Einstein-v6.1-Llama3-8B/tree/main/data)
# 🔄 Quantizationed versions
## GGUF [@bartowski](https://huggingface.co/bartowski)
- https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-GGUF
## ExLlamaV2 [@bartowski](https://huggingface.co/bartowski)
- https://huggingface.co/bartowski/Einstein-v6.1-Llama3-8B-exl2
## AWQ [@solidrust](https://huggingface.co/solidrust)
- https://huggingface.co/solidrust/Einstein-v6.1-Llama3-8B-AWQ
# 🎯 [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_Weyaxi__Einstein-v6.1-Llama3-8B)
| Metric |Value|
|---------------------------------|----:|
|Avg. |68.60|
|AI2 Reasoning Challenge (25-Shot)|62.46|
|HellaSwag (10-Shot) |82.41|
|MMLU (5-Shot) |66.19|
|TruthfulQA (0-shot) |55.10|
|Winogrande (5-shot) |79.32|
|GSM8k (5-shot) |66.11|
# 🤖 Additional information about training
This model is full fine-tuned for 2 epoch.
Total number of steps was 2026.
Loss graph
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6468ce47e134d050a58aa89c/Ycs7ZpoqmxFt0u9rybCO1.png)
# 🤝 Acknowledgments
Thanks to [sablo.ai](https://sablo.ai) for sponsoring this model.
Thanks to all the dataset authors mentioned in the datasets section.
Thanks to [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) for making the repository I used to make this model.
Thanks to all open source AI community.
[](https://github.com/OpenAccess-AI-Collective/axolotl)
If you would like to support me:
[☕ Buy Me a Coffee](https://www.buymeacoffee.com/weyaxi)