Downloads · 30 days
479
11% of all-time downloads
RichardErkhov/flammenai_-_flammen15-gutenberg-DPO-v1-7B-gguf
flammenai_-_flammen15-gutenberg-DPO-v1-7B-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
479
11% of all-time downloads
All-time downloads
4.3K
Public
Repo size
82.2 GB
Likes
0
Public
Click a slice to open those files.
.gguf95.2 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
flammen15-gutenberg-DPO-v1-7B - GGUF
license: apache-2.0 library_name: transformers base_model:

A Mistral 7B LLM built from merging pretrained models and finetuning on Jon Durbin's Gutenberg DPO set. Flammen specializes in exceptional character roleplay, creative writing, and general intelligence
Finetuned using an A100 on Google Colab. (plz give more gpu)
Fine-tune a Mistral-7b model with Direct Preference Optimization - Maxime Labonne
LoRA, model, and training settings:
# 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=2,
gradient_accumulation_steps=2,
gradient_checkpointing=True,
learning_rate=2e-5,
lr_scheduler_type="cosine",
max_steps=200,
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,
max_prompt_length=1024,
max_length=1536,
force_use_ref_model=True
)
# Fine-tune model with DPO
dpo_trainer.train()
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 21.46 |
| IFEval (0-Shot) | 47.98 |
| BBH (3-Shot) | 32.67 |
| MATH Lvl 5 (4-Shot) | 6.72 |
| GPQA (0-shot) | 4.59 |
| MuSR (0-shot) | 12.53 |
| MMLU-PRO (5-shot) | 24.29 |