v4
Collection
18 items
•
Updated
•
23
This is 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 mistralai/Mistral-Large-Instruct-2407.
A typical input would look like this:
<s>[INST] SYSTEM MESSAGE\nUSER MESSAGE[/INST] ASSISTANT MESSAGE</s>[INST] USER MESSAGE[/INST]
Below are Instruct and Context templates for use within SillyTavern.
default SillyTavern template works fine
default SillyTavern template works fine
base_model: mistralai/Mistral-Large-Instruct-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-org/c2_logs_16k_mistral-large_v1.2
type: sharegpt
conversation: mistral
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal
type: sharegpt
conversation: mistral
- path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
type: sharegpt
conversation: mistral
- path: anthracite-org/nopm_claude_writing_fixed
type: sharegpt
conversation: mistral
- path: anthracite-org/kalo_opus_misc_240827
type: sharegpt
conversation: mistral
- path: anthracite-org/kalo_misc_part2
type: sharegpt
conversation: mistral
#chat_template: chatml
shuffle_merged_datasets: true
#default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: ./data/magnum-123b-data
val_set_size: 0.0
output_dir: ./data/123b-fft-out
sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true
adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project: 123b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: alter-attempt-04
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0000015
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
We'd like to thank Eric Hartford for sponsoring the compute for this train. We would also like to thank all members of Anthracite who made this finetune possible.
We used 8x mi300x GPUs graciously provided by Eric Hartford for the full-parameter fine-tuning of the model.
...