Fine-Tuned
Collection
40 items
•
Updated
•
6
axolotl version: 0.4.0
base_model: NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT
model_type: MixtralForCausalLM
tokenizer_type: LlamaTokenizer
trust_remote_code: true
hub_model_id: MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca
hf_use_auth_token: true
load_in_4bit: true
strict: false
datasets:
- path: tatsu-lab/alpaca
type: alpaca
dataset_prepared_path: last_run_prepared
val_set_size: 0.1
output_dir: ./qlora-out
# save_safetensors: true
adapter: qlora
lora_model_dir:
sequence_len: 1024
sample_packing: true
pad_to_sequence_len: true
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:
lora_target_modules:
# - gate
- q_proj
# - k_proj
- v_proj
# - o_proj
# - w1
# - w2
# - w3
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 1
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
This model is a fine-tuned version of NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT on the None dataset. It achieves the following results on the evaluation set:
PEFT
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM
config = PeftConfig.from_pretrained("MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-2-Mixtral-8x7B-SFT")
model = PeftModel.from_pretrained(model, "MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca")
Transformers
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca")
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca")
model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/Nous-Hermes-2-Mixtral-8x7B-SFT-Alpaca")
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.3912 | 0.01 | 1 | 1.3714 |
1.0321 | 0.25 | 45 | 1.0427 |
1.0312 | 0.51 | 90 | 1.0327 |
0.9917 | 0.76 | 135 | 1.0276 |