DeepBlue-Forge-7B

1
license:apache-2.0
by
PCIFIC
Language Model
OTHER
7B params
New
0 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
16GB+ RAM
Mobile
Laptop
Server
Quick Summary

AI model with specialized capabilities.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
7GB+ RAM

Code Examples

yaml
base_model: Qwen/Qwen2.5-7B-Instruct
load_in_8bit: false
load_in_4bit: false
datasets:
  - path: qualcosr/deepblue-forge-ds-1
    type: chat_template
    chat_template: chatml
    field_messages: messages
val_set_size: 0.05
output_dir: ./outputs/listing-generator-qwen-7b-16k
adapter: lora
lora_r: 64
lora_alpha: 128
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - up_proj
  - down_proj
sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true
micro_batch_size: 2
gradient_accumulation_steps: 8
num_epochs: 3
optimizer: adamw_torch_fused
lr_scheduler: cosine
learning_rate: 5e-5
weight_decay: 0.1
warmup_ratio: 0.03
gradient_checkpointing: true
flash_attention: true
bf16: auto
tf32: true
logging_steps: 10
save_steps: 50
eval_steps: 50
save_total_limit: 3
special_tokens:
  pad_token: "<|endoftext|>"

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.