magnum-v2-4b-exl2

This repo contains EXL2 quants of the model. If you need the original weights, please find them here.

Base repo only contains the measurement file, see revisions for your quant of choice.

• measurement.json
• 3.0bpw
• 4.0bpw
• 5.0bpw
• 6.0bpw
• 8.0bpw

This is the eighth in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml.

Prompting

Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:

"""<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""

axolotl config

<details><summary>See axolotl config</summary>

axolotl version: 0.4.1

base_model: IntervitensInc/Llama-3.1-Minitron-4B-Width-Base-chatml
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/Gryphe-3.5-16k-Subset
    type: sharegpt
    conversation: chatml
  - path: Epiculous/Synthstruct-Gens-v1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/Stheno-Data-Filtered
    type: sharegpt
    conversation: chatml
  - path: Epiculous/SynthRP-Gens-v1-Filtered-n-Cleaned
    type: sharegpt
    conversation: chatml
  - path: lodrick-the-lafted/NopmWritingStruct
    type: sharegpt
    conversation: chatml
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal
    type: sharegpt
    conversation: chatml

chat_template: chatml

val_set_size: 0.01
output_dir: ./outputs/out

adapter:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:

sequence_len: 16384
# sequence_len: 32768
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true

wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 32
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00002
weight_decay: 0.05

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: true

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_ratio: 0.1
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1

debug:
deepspeed:
fsdp:
fsdp_config:

special_tokens:
  pad_token: <|finetune_right_pad_id|>

</details><br>

Credits

• anthracite-org/Stheno-Data-Filtered
• anthracite-org/kalo-opus-instruct-22k-no-refusal
• lodrick-the-lafted/NopmWritingStruct
• NewEden/Gryphe-3.5-16k-Subset
• Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
• Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned

This model has been a team effort, and the credits goes to all members of Anthracite.

Training

The training was done for 2 epochs. We used 2 x RTX 6000s GPUs graciously provided by Kubernetes_Bad for the full-parameter fine-tuning of the model.

<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>

Safety

...