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-Nemo-Instruct-2407.
Prompting
A typical input would look like this:
<s>[INST] SYSTEM MESSAGE
USER MESSAGE[/INST] ASSISTANT MESSAGE</s>[INST] USER MESSAGE[/INST]
SillyTavern templates
Below are Instruct and Context templates for use within SillyTavern.
context template
default SillyTavern template works fine
instruct template
default SillyTavern template works fine
Axolotl config
See axolotl config
base_model: mistralai/Mistral-Nemo-Instruct-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
hub_model_id: anthracite-org/magnum-v4-12b-r2
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true
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_32k_llama3_qwen2_v1.2_no_system
type: custommistralv3tekken
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
type: custommistralv3tekken
- path: anthracite-org/kalo-opus-instruct-3k-filtered-no-system
type: custommistralv3tekken
- path: anthracite-org/nopm_claude_writing_fixed
type: custommistralv3tekken
- path: anthracite-org/kalo_opus_misc_240827_no_system
type: custommistralv3tekken
- path: anthracite-org/kalo_misc_part2_no_system
type: custommistralv3tekken
#chat_template: chatml
shuffle_merged_datasets: true
#default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: /workspace/data/magnum-12b-data
val_set_size: 0.0
output_dir: /workspace/data/12b-fft-out
sequence_len: 32768
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: 12b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: v4-r2-attempt-01
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
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/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>
Credits
We'd like to thank Recursal / Featherless for sponsoring the compute for this train, Featherless has been hosting our Magnum models since the first 72 B and has given thousands of people access to our models and helped us grow.
We would also like to thank all members of Anthracite who made this finetune possible.
Datasets
- anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system
- anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
- anthracite-org/kalo-opus-instruct-3k-filtered-no-system
- anthracite-org/nopm_claude_writing_fixed
- anthracite-org/kalo_opus_misc_240827_no_system
- anthracite-org/kalo_misc_part2_no_system
Training
The training was done for 2 epochs. We used 8xH100s GPUs graciously provided by Recursal AI / Featherless AI for the full-parameter fine-tuning of the model.
Safety
...
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 19.95 |
IFEval (0-Shot) | 33.93 |
BBH (3-Shot) | 30.50 |
MATH Lvl 5 (4-Shot) | 9.82 |
GPQA (0-shot) | 6.15 |
MuSR (0-shot) | 10.36 |
MMLU-PRO (5-shot) | 28.93 |
- Downloads last month
- 837
Model tree for anthracite-org/magnum-v4-12b
Datasets used to train anthracite-org/magnum-v4-12b
Spaces using anthracite-org/magnum-v4-12b 2
Collection including anthracite-org/magnum-v4-12b
Evaluation results
- strict accuracy on IFEval (0-Shot)Open LLM Leaderboard33.930
- normalized accuracy on BBH (3-Shot)Open LLM Leaderboard30.500
- exact match on MATH Lvl 5 (4-Shot)Open LLM Leaderboard9.820
- acc_norm on GPQA (0-shot)Open LLM Leaderboard6.150
- acc_norm on MuSR (0-shot)Open LLM Leaderboard10.360
- accuracy on MMLU-PRO (5-shot)test set Open LLM Leaderboard28.930