license: gemma
base_model: IntervitensInc/gemma-2-9b-chatml
model-index:
- name: magnum-v3-9b-chatml
results: []
This repo contains GGUF quants of the model. If you need the original weights, please find them here.
This is the 11th 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/gemma-2-9b-chatml. (chatMLified gemma-2-9b)
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
"""
SillyTavern templates
Below are Instruct and Context templates for use within SillyTavern.
context template
{
"story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>\n",
"example_separator": "",
"chat_start": "",
"use_stop_strings": false,
"allow_jailbreak": false,
"always_force_name2": true,
"trim_sentences": false,
"include_newline": false,
"single_line": false,
"name": "Magnum ChatML"
}
instruct template
{
"system_prompt": "You're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.",
"input_sequence": "<|im_start|>user\n",
"output_sequence": "<|im_start|>assistant\n",
"last_output_sequence": "",
"system_sequence": "<|im_start|>system\n",
"stop_sequence": "<|im_end|>",
"wrap": false,
"macro": true,
"names": true,
"names_force_groups": true,
"activation_regex": "",
"system_sequence_prefix": "",
"system_sequence_suffix": "",
"first_output_sequence": "",
"skip_examples": false,
"output_suffix": "<|im_end|>\n",
"input_suffix": "<|im_end|>\n",
"system_suffix": "<|im_end|>\n",
"user_alignment_message": "",
"system_same_as_user": false,
"last_system_sequence": "",
"name": "Magnum ChatML"
}
Axolotl config
See axolotl config
base_model: IntervitensInc/gemma-2-9b-chatml
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
#trust_remote_code: true
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: anthracite-org/stheno-filtered-v1.1
type: sharegpt
conversation: chatml
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal
type: sharegpt
conversation: chatml
- path: anthracite-org/nopm_claude_writing_fixed
type: sharegpt
conversation: chatml
- path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
type: sharegpt
conversation: chatml
- path: Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
type: sharegpt
conversation: chatml
shuffle_merged_datasets: true
default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: magnum-v3-9b-data-chatml
val_set_size: 0.0
output_dir: ./magnum-v3-9b-chatml
sequence_len: 8192
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len:
adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project: magnum-9b
wandb_entity:
wandb_watch:
wandb_name: attempt-04-chatml
wandb_log_model:
gradient_accumulation_steps: 8
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.000006
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: false
eager_attention: true
warmup_steps: 50
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.05
fsdp:
fsdp_config:
special_tokens:
Credits
We'd like to thank Recursal / Featherless for sponsoring the training compute required for this model. Featherless has been hosting Magnum since the original 72b and has given thousands of people access to our releases.
We would also like to thank all members of Anthracite who made this finetune possible.
- anthracite-org/stheno-filtered-v1.1
- anthracite-org/kalo-opus-instruct-22k-no-refusal
- anthracite-org/nopm_claude_writing_fixed
- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
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
...