|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: google/gemma-7b-it |
|
tags: |
|
- generated_from_trainer |
|
- axolotl |
|
- gemma |
|
- instruct |
|
- finetune |
|
- chatml |
|
- gpt4 |
|
- synthetic data |
|
- distillation |
|
model-index: |
|
- name: gemma-7b-openhermes |
|
results: [] |
|
datasets: |
|
- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha |
|
language: |
|
- en |
|
library_name: transformers |
|
pipeline_tag: text-generation |
|
--- |
|
<!-- 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. --> |
|
|
|
# gemma-7b-openhermes |
|
|
|
|
|
|
|
 |
|
|
|
gemma-7b-openhermes is a variant of the Gemma 7B language model, which has been further fine-tuned on the OpenHermes-2.5 preference dataset |
|
using QLoRA. |
|
|
|
|
|
* [google/gemma-7b-it](https://huggingface.co/google/gemma-7b-it) |
|
* [mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha](https://huggingface.co/datasets/mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha) |
|
|
|
</details><br> |
|
|
|
## Usage |
|
|
|
### Chat Template |
|
|
|
The instruction-tuned models use a chat template that must be adhered to for conversational use. |
|
The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet. |
|
|
|
Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction: |
|
|
|
```py |
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
import transformers |
|
import torch |
|
|
|
model_id = "abideen/gemma-7b-openhermes" |
|
dtype = torch.bfloat16 |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_id, |
|
device_map="cuda", |
|
torch_dtype=dtype, |
|
) |
|
|
|
chat = [{ "role": "user", "content": "What is a Language Model?" }] |
|
prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) |
|
``` |
|
|
|
After the prompt is ready, generation can be performed like this: |
|
|
|
```py |
|
inputs = tokenizer.encode(prompt, add_special_tokens=True, return_tensors="pt") |
|
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=250) |
|
print(tokenizer.decode(outputs[0])) |
|
``` |
|
|
|
### Inputs and outputs |
|
|
|
* **Input:** Text string, such as a question, a prompt, or a document to be |
|
summarized. |
|
* **Output:** Generated English-language text in response to the input, such |
|
as an answer to a question, or a summary of a document. |
|
|
|
## 🏆 Evaluation results |
|
|
|
# Nous Benchmark |
|
|
|
Agieval |
|
|
|
| Task | Version | Metric | Value | | StdErr | |
|
|-------------------------------------------|---------|--------|-------|---|---------| |
|
| agieval\_aqua\_rat | 0 | acc | 24.80 | _ | 2.72 | |
|
| agieval\_aqua\_rat | 0 | acc\_norm | 24.80 | _ | 2.72 | |
|
| agieval\_logiqa\_en | 0 | acc | 20.89 | _ | 1.59 | |
|
| agieval\_logiqa\_en | 0 | acc\_norm | 23.35 | _ | 1.66 | |
|
| agieval\_lsat\_ar | 0 | acc | 21.74 | _ | 2.73 | |
|
| agieval\_lsat\_ar | 0 | acc\_norm | 20.43 | _ | 2.66 | |
|
| agieval\_lsat\_lr | 0 | acc | 15.49 | _ | 1.60 | |
|
| agieval\_lsat\_lr | 0 | acc\_norm | 20.59 | _ | 1.79 | |
|
| agieval\_lsat\_rc | 0 | acc | 17.10 | _ | 2.30 | |
|
| agieval\_lsat\_rc | 0 | acc\_norm | 17.84 | _ | 2.34 | |
|
| agieval\_sat\_en | 0 | acc | 29.61 | _ | 3.19 | |
|
| agieval\_sat\_en | 0 | acc\_norm | 29.61 | _ | 3.19 | |
|
| agieval\_sat\_en\_without\_passage | 0 | acc | 26.21 | _ | 3.07 | |
|
| agieval\_sat\_en\_without\_passage | 0 | acc\_norm | 24.76 | _ | 3.01 | |
|
| agieval\_sat\_math | 0 | acc | 22.73 | _ | 2.83 | |
|
| agieval\_sat\_math | 0 | acc\_norm | 22.73 | _ | 2.83 | |
|
Average: 22.29 |
|
|
|
GPT4ALL |
|
|
|
| Task | Version | Metric | Value | | StdErr | |
|
|---------------|---------|------------|---------|---|-------------| |
|
| arc_challenge | 0 | acc | 20.14 | _ | 1.17 | |
|
| arc_challenge | 0 | acc_norm | 22.87 | _ | 1.23 | |
|
| arc_easy | 0 | acc | 32.37 | _ | 0.96 | |
|
| arc_easy | 0 | acc_norm | 31.61 | _ | 0.95 | |
|
| boolq | 1 | acc | 45.78 | _ | 0.87 | |
|
| hellaswag | 0 | acc | 32.03 | _ | 0.47 | |
|
| hellaswag | 0 | acc_norm | 35.18 | _ | 0.48 | |
|
| openbookqa | 0 | acc | 17.8 | _ | 1.71 | |
|
| openbookqa | 0 | acc_norm | 29.8 | _ | 2.05 | |
|
| piqa | 0 | acc | 54.46 | _ | 1.16 | |
|
| piqa | 0 | acc_norm | 54.57 | _ | 1.16 | |
|
| winogrande | 0 | acc | 48.30 | _ | 1.40 | |
|
Average: 32.00 |
|
|
|
|
|
TruthfulQA |
|
|
|
| Task | Version | Metric | Value | Std Err | |
|
|----------------------------------|---------|--------|--------|----------| |
|
| truthfulqa\_mc | 1 | mc1 | 30.11 | 1.61 | |
|
| truthfulqa\_mc | 1 | mc2 | 47.69 | 1.61 | |
|
Average: 38.90 |
|
|
|
|
|
# Openllm Benchmark |
|
|
|
| Task |Version| Metric |Value| |Stderr| |
|
|-------------|------:|--------|----:|---|-----:| |
|
|arc_challenge| 0|acc |48.12|± | 1.46| |
|
| | |acc_norm|51.27|± | 1.46| |
|
|hellaswag | 0|acc |55.4 |± | 0.49| |
|
| | |acc_norm|71.92|± | 0.42| |
|
|gsm8k | 0|acc |29.87|± | 1.2 | |
|
|winogrande | 0|acc |68.19|± | 1.3 | |
|
|mmlu | 0|acc |53.62 |±| 0.6 | |
|
|
|
Average: 73.5% |
|
|
|
### TruthfulQA |
|
| Task |Version|Metric|Value| |Stderr| |
|
|-------------|------:|------|----:|---|-----:| |
|
|truthfulqa_mc| 1|mc1 |30.23|± | 1.60| |
|
| | |mc2 |47.17|± | 1.63| |
|
|
|
|
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-07 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- 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: 100 |
|
- training_steps: 1000 |
|
|
|
|
|
### 📝 Axolotl Configuration |
|
|
|
```yaml |
|
base_model: google/gemma-7b-it |
|
model_type: GemmaForCausalLM |
|
tokenizer_type: GemmaTokenizer |
|
trust_remote_code: true |
|
|
|
load_in_8bit: false |
|
load_in_4bit: true |
|
strict: false |
|
|
|
rl: dpo |
|
chat_template: chatml |
|
datasets: |
|
- path: mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha |
|
split: train |
|
type: chatml.intel |
|
dataset_prepared_path: |
|
val_set_size: 0.01 |
|
output_dir: ./out |
|
|
|
adapter: qlora |
|
lora_model_dir: |
|
|
|
sequence_len: 1800 |
|
sample_packing: false |
|
pad_to_sequence_len: false |
|
|
|
lora_r: 16 |
|
lora_alpha: 16 |
|
lora_dropout: 0.05 |
|
lora_target_linear: true |
|
lora_fan_in_fan_out: |
|
lora_target_modules: |
|
|
|
wandb_project: gemma |
|
wandb_entity: |
|
wandb_watch: |
|
wandb_name: |
|
wandb_log_model: |
|
|
|
gradient_accumulation_steps: 8 |
|
micro_batch_size: 1 |
|
num_epochs: 1 |
|
optimizer: paged_adamw_32bit |
|
lr_scheduler: cosine |
|
learning_rate: 5e-7 |
|
|
|
train_on_inputs: false |
|
group_by_length: false |
|
bf16: true |
|
fp16: false |
|
tf32: true |
|
|
|
gradient_checkpointing: true |
|
early_stopping_patience: |
|
resume_from_checkpoint: |
|
local_rank: |
|
logging_steps: 1 |
|
xformers_attention: |
|
flash_attention: false |
|
|
|
warmup_steps: 100 |
|
evals_per_epoch: 1 |
|
eval_table_size: |
|
eval_table_max_new_tokens: 128 |
|
save_steps: 1000 |
|
max_steps: 1000 |
|
debug: |
|
deepspeed: |
|
weight_decay: 0.0 |
|
fsdp: |
|
fsdp_config: |
|
special_tokens: |
|
``` |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.1.2+cu118 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.0 |
|
- axolotl: 0.4.0 |
|
|
|
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) |
