|
--- |
|
library_name: transformers |
|
license: llama3 |
|
base_model: |
|
- nbeerbower/llama-3-Stheno-Mahou-8B |
|
datasets: |
|
- flammenai/FlameMix-DPO-v1 |
|
- flammenai/Grill-preprod-v1_chatML |
|
- flammenai/Grill-preprod-v2_chatML |
|
--- |
|
**Exllamav2** quant (**exl2** / **3.0 bpw**) made with ExLlamaV2 v0.0.21 |
|
|
|
Other EXL2 quants: |
|
| **Quant** | **Model Size** | **lm_head** | |
|
| ----- | ---------- | ------- | |
|
|<center>**[2.2](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-2_2bpw_exl2)**</center> | <center>3250 MB</center> | <center>6</center> | |
|
|<center>**[2.5](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-2_5bpw_exl2)**</center> | <center>3479 MB</center> | <center>6</center> | |
|
|<center>**[3.0](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-3_0bpw_exl2)**</center> | <center>3893 MB</center> | <center>6</center> | |
|
|<center>**[3.5](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-3_5bpw_exl2)**</center> | <center>4311 MB</center> | <center>6</center> | |
|
|<center>**[3.75](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-3_75bpw_exl2)**</center> | <center>4518 MB</center> | <center>6</center> | |
|
|<center>**[4.0](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-4_0bpw_exl2)**</center> | <center>4727 MB</center> | <center>6</center> | |
|
|<center>**[4.25](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-4_25bpw_exl2)**</center> | <center>4935 MB</center> | <center>6</center> | |
|
|<center>**[5.0](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-5_0bpw_exl2)**</center> | <center>5557 MB</center> | <center>6</center> | |
|
|<center>**[6.0](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-6_0bpw_exl2)**</center> | <center>6496 MB</center> | <center>8</center> | |
|
|<center>**[6.5](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-6_5bpw_exl2)**</center> | <center>6902 MB</center> | <center>8</center> | |
|
|<center>**[8.0](https://huggingface.co/Zoyd/flammenai_Mahou-1.2a-llama3-8B-8_0bpw_exl2)**</center> | <center>8131 MB</center> | <center>8</center> | |
|
|
|
![image/png](https://huggingface.co/flammenai/Mahou-1.0-mistral-7B/resolve/main/mahou1.png) |
|
|
|
# Mahou-1.2a-llama3-8B |
|
|
|
Mahou is our attempt to build a production-ready conversational/roleplay LLM. |
|
|
|
Future versions will be released iteratively and finetuned from flammen.ai conversational data. |
|
|
|
### Chat Format |
|
|
|
This model has been trained to use ChatML format. |
|
|
|
``` |
|
<|im_start|>system |
|
{{system}}<|im_end|> |
|
<|im_start|>{{char}} |
|
{{message}}<|im_end|> |
|
<|im_start|>{{user}} |
|
{{message}}<|im_end|> |
|
``` |
|
|
|
# Roleplay Format |
|
|
|
- Speech without quotes. |
|
- Actions in `*asterisks*` |
|
|
|
``` |
|
*leans against wall cooly* so like, i just casted a super strong spell at magician academy today, not gonna lie, felt badass. |
|
``` |
|
|
|
### ST Settings |
|
|
|
1. Use ChatML for the Context Template. |
|
2. Turn on Instruct Mode for ChatML. |
|
3. Use the following stopping strings: `["<", "|", "<|", "\n"]` |
|
|
|
### Method |
|
|
|
Finetuned using an A100 on Google Colab. |
|
|
|
[Fine-tune a Mistral-7b model with Direct Preference Optimization](https://towardsdatascience.com/fine-tune-a-mistral-7b-model-with-direct-preference-optimization-708042745aac) - [Maxime Labonne](https://huggingface.co/mlabonne) |
|
|
|
### Configuration |
|
|
|
LoRA, model, and training settings: |
|
|
|
```python |
|
# LoRA configuration |
|
peft_config = LoraConfig( |
|
r=16, |
|
lora_alpha=16, |
|
lora_dropout=0.05, |
|
bias="none", |
|
task_type="CAUSAL_LM", |
|
target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj'] |
|
) |
|
|
|
# Model to fine-tune |
|
model = AutoModelForCausalLM.from_pretrained( |
|
model_name, |
|
torch_dtype=torch.bfloat16, |
|
load_in_4bit=True |
|
) |
|
model.config.use_cache = False |
|
|
|
# Reference model |
|
ref_model = AutoModelForCausalLM.from_pretrained( |
|
model_name, |
|
torch_dtype=torch.bfloat16, |
|
load_in_4bit=True |
|
) |
|
|
|
# Training arguments |
|
training_args = TrainingArguments( |
|
per_device_train_batch_size=4, |
|
gradient_accumulation_steps=4, |
|
gradient_checkpointing=True, |
|
learning_rate=5e-5, |
|
lr_scheduler_type="cosine", |
|
max_steps=2000, |
|
save_strategy="no", |
|
logging_steps=1, |
|
output_dir=new_model, |
|
optim="paged_adamw_32bit", |
|
warmup_steps=100, |
|
bf16=True, |
|
report_to="wandb", |
|
) |
|
|
|
# Create DPO trainer |
|
dpo_trainer = DPOTrainer( |
|
model, |
|
ref_model, |
|
args=training_args, |
|
train_dataset=dataset, |
|
tokenizer=tokenizer, |
|
peft_config=peft_config, |
|
beta=0.1, |
|
force_use_ref_model=True |
|
) |
|
|
|
# Fine-tune model with DPO |
|
dpo_trainer.train() |
|
``` |