prxy5606__98345738-30aa-41c4-bf69-2392a1ce4d0a
1
llama
by
jjee2
Other
OTHER
8B params
New
0 downloads
Early-stage
Edge AI:
Mobile
Laptop
Server
18GB+ RAM
Mobile
Laptop
Server
Quick Summary
AI model with specialized capabilities.
Device Compatibility
Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
8GB+ RAM
Code Examples
yaml
adapter: lora
base_model: unsloth/Meta-Llama-3.1-8B-Instruct
bf16: true
chat_template: llama3
data_processes: 16
dataset_prepared_path: null
datasets:
- data_files:
- c9e5168aaf615a7c_train_data.json
ds_type: json
format: custom
path: /workspace/input_data/c9e5168aaf615a7c_train_data.json
type:
field_instruction: problem
field_output: target_answer
format: '{instruction}'
no_input_format: '{instruction}'
system_format: '{system}'
system_prompt: ''
debug: null
deepspeed: null
device_map: auto
do_eval: true
early_stopping_patience: 5
eval_batch_size: 4
eval_max_new_tokens: 128
eval_steps: 50
eval_table_size: null
evals_per_epoch: null
flash_attention: true
fp16: false
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: true
hub_model_id: prxy5606/98345738-30aa-41c4-bf69-2392a1ce4d0a
hub_repo: null
hub_strategy: checkpoint
hub_token: null
learning_rate: 0.0001
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 128
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 64
lora_target_linear: true
lr_scheduler: cosine
max_grad_norm: 1.0
max_memory:
0: 75GB
max_steps: 200
micro_batch_size: 8
mlflow_experiment_name: /tmp/c9e5168aaf615a7c_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 3
optim_args:
adam_beta1: 0.9
adam_beta2: 0.95
adam_epsilon: 1e-5
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_steps: 50
saves_per_epoch: null
sequence_len: 1024
strict: false
tf32: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.05
wandb_entity: null
wandb_mode: online
wandb_name: c81d855a-5c46-46dc-bab6-9f15fcbfa230
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: c81d855a-5c46-46dc-bab6-9f15fcbfa230
warmup_steps: 10
weight_decay: 0.0
xformers_attention: nullDeploy This Model
Production-ready deployment in minutes
Together.ai
Instant API access to this model
Production-ready inference API. Start free, scale to millions.
Try Free APIReplicate
One-click model deployment
Run models in the cloud with simple API. No DevOps required.
Deploy NowDisclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.