Downloads · 30 days
1
6% of all-time downloads
Llama-3.3-70B-chem-scieng
cgifbribcgfbi/Llama-3.3-70B-chem-scieng
Llama-3.3-70B-chem-scieng is a machine learning model from cgifbribcgfbi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.3.
should probably proofread and complete it, then remove this comment. --
All-time downloads
16
Public
Repo size
13.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.3 GB · 99%
At a glance
- Library
- peft
- License
- llama3.3
- Model type
- llama
- Access
- Public
- Created
- Jun 21, 2025
- Updated
- Jun 21, 2025
- SHA
- 7426c4fb
Base models
Datasets
Model card
From the Hugging Face model README
<!-- 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. -->
<details><summary>See axolotl config</summary>
axolotl version: 0.10.0
base_model: huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned
load_in_8bit: false
load_in_4bit: true
adapter: qlora
wandb_name: Llama-3.3-70B-chem-scieng
output_dir: ./outputs/out/Llama-3.3-70B-chem-scieng
hub_model_id: cgifbribcgfbi/Llama-3.3-70B-chem-scieng
tokenizer_type: AutoTokenizer
push_dataset_to_hub:
strict: false
datasets:
- path: scieng_5000.jsonl
type: chat_template
field_messages: messages
dataset_prepared_path: last_run_prepared
# val_set_size: 0.05
# eval_sample_packing: False
save_safetensors: true
sequence_len: 2691
sample_packing: true
pad_to_sequence_len: true
lora_r: 64
lora_alpha: 32
lora_dropout: 0.05
lora_target_modules:
- q_proj
- k_proj
- v_proj
- o_proj
- gate_proj
- up_proj
- down_proj
lora_target_linear: false
lora_modules_to_save:
wandb_mode:
wandb_project: finetune-sweep
wandb_entity: gpoisjgqetpadsfke
wandb_watch:
wandb_run_id:
wandb_log_model:
gradient_accumulation_steps: 1
micro_batch_size: 4 # This will be automatically adjusted based on available GPU memory
num_epochs: 4
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 0.00002
train_on_inputs: false
group_by_length: true
bf16: true
tf32: true
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: true
logging_steps: 1
flash_attention: true
warmup_steps: 10
evals_per_epoch: 3
saves_per_epoch: 1
weight_decay: 0.01
fsdp:
- full_shard
- auto_wrap
fsdp_config:
fsdp_limit_all_gathers: true
fsdp_sync_module_states: true
fsdp_offload_params: false
fsdp_use_orig_params: false
fsdp_cpu_ram_efficient_loading: true
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_transformer_layer_cls_to_wrap: LlamaDecoderLayer
fsdp_state_dict_type: FULL_STATE_DICT
fsdp_sharding_strategy: FULL_SHARD
special_tokens:
pad_token: <|finetune_right_pad_id|>
Llama-3.3-70B-chem-scieng
This model is a fine-tuned version of huihui-ai/Llama-3.3-70B-Instruct-abliterated-finetuned on the scieng_5000.jsonl dataset.
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- training_steps: 816
Training results
Framework versions
- PEFT 0.15.2
- Transformers 4.52.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Library
- peft
- Type
- llama
- License
- llama3.3
- Created
- Jun 21, 2025
- Updated
- Jun 21, 2025