---
license: other
license_name: mrl
language:
- en
tags:
- chat
pipeline_tag: text-generation
library_name: transformers
---

![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/WvQykcYiK13x7sMI93T6e.png)
## This repo contains GGUF quants of the model. If you need the original weights, please find them [here](https://huggingface.co/anthracite-org/magnum-v4-22b).

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 [Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409).

## Prompting
A typical input would look like this:

```py
<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.

<details><summary>context template</summary>
  
```yaml
default SillyTavern template works fine
```

</details><br>
<details><summary>instruct template</summary>
  
```yaml
default SillyTavern template works fine
```

</details><br>

## Axolotl config

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

```yaml
base_model: /workspace/models/Mistral-Small-Instruct-2409
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: anthracite-org/magnum-v4-22b-r4
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_cross_entropy: true
liger_fused_linear_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system
    type: custommistralv2v3
  - path: anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
    type: custommistralv2v3
  - path: anthracite-org/kalo-opus-instruct-3k-filtered-no-system
    type: custommistralv2v3
  - path: anthracite-org/nopm_claude_writing_fixed
    type: custommistralv2v3
  - path: anthracite-org/kalo_opus_misc_240827_no_system
    type: custommistralv2v3
  - path: anthracite-org/kalo_misc_part2_no_system
    type: custommistralv2v3
#chat_template: mistral_v2v3
shuffle_merged_datasets: true
#default_system_message: "You are an assistant that responds to the user."
dataset_prepared_path: /workspace/data/magnum-22b-data
val_set_size: 0.0
output_dir: /workspace/data/22b-r4-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: 22b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: v4-r4-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: 0.000004

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/zero3_bf16.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
```
</details><br>

## 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_mistral-v3_v1.2_no_system](https://huggingface.co/datasets/anthracite-org/c2_logs_32k_mistral-v3_v1.2_no_system)
- [anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system)
- [anthracite-org/kalo-opus-instruct-3k-filtered-no-system](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-3k-filtered-no-system)
- [anthracite-org/nopm_claude_writing_fixed](https://huggingface.co/datasets/anthracite-org/nopm_claude_writing_fixed)
- [anthracite-org/kalo_opus_misc_240827_no_system](https://huggingface.co/datasets/anthracite-org/kalo_opus_misc_240827_no_system)
- [anthracite-org/kalo_misc_part2_no_system](https://huggingface.co/datasets/anthracite-org/kalo_misc_part2_no_system)

## Training
The training was done for 2 epochs. We used  8x[H100s](https://www.nvidia.com/en-us/data-center/h100/) GPUs graciously provided by [Recursal AI](https://recursal.ai/) / [Featherless AI](https://featherless.ai/) 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"/>](https://github.com/OpenAccess-AI-Collective/axolotl)

## Safety
...