---
license: gemma
library_name: transformers
tags:
- gemma-2
base_model:
- anthracite-forge/magnum-v3-27b-kto-r3
- anthracite-forge/magnum-v3-27b-KTO-e1-r2
- anthracite-forge/magnum-v3-27b-KTO-e0.25-r1
- IntervitensInc/gemma-2-27b-chatml
pipeline_tag: text-generation
model-index:
- name: magnum-v3-27b-kto
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: ENEM Challenge (No Images)
type: eduagarcia/enem_challenge
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 74.88
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BLUEX (No Images)
type: eduagarcia-temp/BLUEX_without_images
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 64.67
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: OAB Exams
type: eduagarcia/oab_exams
split: train
args:
num_few_shot: 3
metrics:
- type: acc
value: 56.36
name: accuracy
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 RTE
type: assin2
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 92.35
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Assin2 STS
type: eduagarcia/portuguese_benchmark
split: test
args:
num_few_shot: 15
metrics:
- type: pearson
value: 80.24
name: pearson
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: FaQuAD NLI
type: ruanchaves/faquad-nli
split: test
args:
num_few_shot: 15
metrics:
- type: f1_macro
value: 73.61
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HateBR Binary
type: ruanchaves/hatebr
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 75.97
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: PT Hate Speech Binary
type: hate_speech_portuguese
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 71.35
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: tweetSentBR
type: eduagarcia/tweetsentbr_fewshot
split: test
args:
num_few_shot: 25
metrics:
- type: f1_macro
value: 68.8
name: f1-macro
source:
url: https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard?query=anthracite-org/magnum-v3-27b-kto
name: Open Portuguese LLM Leaderboard
---
![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/GKpV5mwmnHFR6wIwTa91z.png)
This is the 12th in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus.
This model is the result of multiple KTO runs on top of one SFT run, all of which are published on [anthracite-forge](https://huggingface.co/anthracite-forge).
## Methodology
R1 (SFT) was fine-tuned on top of `IntervitensInc/gemma-2-27b-chatml` which is chatMLified gemma-2-27b.
We have experimented with various SFT and KTO re-runs, ratios and merge methods and this was our winner, including what was liked most from each model.
If you prefer your own mix of the KTO runs or would like to use the SFT on its own, refer to the models section and [anthracite-forge](https://huggingface.co/anthracite-forge), some exl-quants are pre-included.
## Models
* [anthracite-forge/magnum-v3-27b-kto-r3](https://huggingface.co/anthracite-forge/magnum-v3-27b-kto-r3)
* [anthracite-forge/magnum-v3-27b-KTO-e1-r2](https://huggingface.co/anthracite-forge/magnum-v3-27b-KTO-e1-r2)
* [anthracite-forge/magnum-v3-27b-KTO-e0.25-r1](https://huggingface.co/anthracite-forge/magnum-v3-27b-KTO-e0.25-r1)
## Prompting
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
```py
"""<|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
```yaml
{
"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
```yaml
{
"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"
}
```
### Configuration
```yaml
base_model: IntervitensInc/gemma-2-27b-chatml
dtype: float32
merge_method: task_arithmetic
models:
- model: IntervitensInc/gemma-2-27b-chatml
- model: anthracite-forge/magnum-v3-27b-KTO-e0.25-r1
parameters:
weight: 0.5
- model: anthracite-forge/magnum-v3-27b-KTO-e1-r2
parameters:
weight: 0.1
- model: anthracite-forge/magnum-v3-27b-kto-r3
parameters:
weight: 0.4
```
## 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
r1 consisted of:
```
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
```
## 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.
[](https://github.com/OpenAccess-AI-Collective/axolotl)
## Safety
...
# Open Portuguese LLM Leaderboard Evaluation Results
Detailed results can be found [here](https://huggingface.co/datasets/eduagarcia-temp/llm_pt_leaderboard_raw_results/tree/main/anthracite-org/magnum-v3-27b-kto) and on the [🚀 Open Portuguese LLM Leaderboard](https://huggingface.co/spaces/eduagarcia/open_pt_llm_leaderboard)
| Metric | Value |
|--------------------------|---------|
|Average |**73.14**|
|ENEM Challenge (No Images)| 74.88|
|BLUEX (No Images) | 64.67|
|OAB Exams | 56.36|
|Assin2 RTE | 92.35|
|Assin2 STS | 80.24|
|FaQuAD NLI | 73.61|
|HateBR Binary | 75.97|
|PT Hate Speech Binary | 71.35|
|tweetSentBR | 68.80|