You can deploy this model and start earning money today!

RichardErkhov/
Trappu_-_Magnum-Picaro-0.7-v2-12b-gguf

Name: Trappu_-_Magnum-Picaro-0.7-v2-12b-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Magnum-Picaro-0.7-v2-12b - GGUF

Model creator: https://huggingface.co/Trappu/
Original model: https://huggingface.co/Trappu/Magnum-Picaro-0.7-v2-12b/

Name	Quant method	Size
Magnum-Picaro-0.7-v2-12b.Q2_K.gguf	Q2_K	4.46GB
Magnum-Picaro-0.7-v2-12b.IQ3_XS.gguf	IQ3_XS	4.94GB
Magnum-Picaro-0.7-v2-12b.IQ3_S.gguf	IQ3_S	5.18GB
Magnum-Picaro-0.7-v2-12b.Q3_K_S.gguf	Q3_K_S	5.15GB
Magnum-Picaro-0.7-v2-12b.IQ3_M.gguf	IQ3_M	5.33GB
Magnum-Picaro-0.7-v2-12b.Q3_K.gguf	Q3_K	5.67GB
Magnum-Picaro-0.7-v2-12b.Q3_K_M.gguf	Q3_K_M	5.67GB
Magnum-Picaro-0.7-v2-12b.Q3_K_L.gguf	Q3_K_L	6.11GB
Magnum-Picaro-0.7-v2-12b.IQ4_XS.gguf	IQ4_XS	6.33GB
Magnum-Picaro-0.7-v2-12b.Q4_0.gguf	Q4_0	6.59GB
Magnum-Picaro-0.7-v2-12b.IQ4_NL.gguf	IQ4_NL	6.65GB
Magnum-Picaro-0.7-v2-12b.Q4_K_S.gguf	Q4_K_S	6.63GB
Magnum-Picaro-0.7-v2-12b.Q4_K.gguf	Q4_K	6.96GB
Magnum-Picaro-0.7-v2-12b.Q4_K_M.gguf	Q4_K_M	6.96GB
Magnum-Picaro-0.7-v2-12b.Q4_1.gguf	Q4_1	7.26GB
Magnum-Picaro-0.7-v2-12b.Q5_0.gguf	Q5_0	7.93GB
Magnum-Picaro-0.7-v2-12b.Q5_K_S.gguf	Q5_K_S	7.93GB
Magnum-Picaro-0.7-v2-12b.Q5_K.gguf	Q5_K	8.13GB
Magnum-Picaro-0.7-v2-12b.Q5_K_M.gguf	Q5_K_M	8.13GB
Magnum-Picaro-0.7-v2-12b.Q5_1.gguf	Q5_1	8.61GB
Magnum-Picaro-0.7-v2-12b.Q6_K.gguf	Q6_K	9.37GB
Magnum-Picaro-0.7-v2-12b.Q8_0.gguf	Q8_0	12.13GB

Original model description:

tags:

merge
mergekit
lazymergekit
anthracite-org/magnum-v2-12b
Trappu/Nemo-Picaro-12B base_model:
anthracite-org/magnum-v2-12b
Trappu/Nemo-Picaro-12B model-index:
name: Magnum-Picaro-0.7-v2-12b results:
- task: type: text-generation name: Text Generation dataset: name: IFEval (0-Shot) type: HuggingFaceH4/ifeval args: num_few_shot: 0 metrics:
  - type: inst_level_strict_acc and prompt_level_strict_acc value: 30.03 name: strict accuracy source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: BBH (3-Shot) type: BBH args: num_few_shot: 3 metrics:
  - type: acc_norm value: 35.75 name: normalized accuracy source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MATH Lvl 5 (4-Shot) type: hendrycks/competition_math args: num_few_shot: 4 metrics:
  - type: exact_match value: 4.76 name: exact match source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: GPQA (0-shot) type: Idavidrein/gpqa args: num_few_shot: 0 metrics:
  - type: acc_norm value: 9.73 name: acc_norm source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MuSR (0-shot) type: TAUR-Lab/MuSR args: num_few_shot: 0 metrics:
  - type: acc_norm value: 19.56 name: acc_norm source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b name: Open LLM Leaderboard
- task: type: text-generation name: Text Generation dataset: name: MMLU-PRO (5-shot) type: TIGER-Lab/MMLU-Pro config: main split: test args: num_few_shot: 5 metrics:
  - type: acc value: 28.67 name: accuracy source: url: >- https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b name: Open LLM Leaderboard license: apache-2.0 pipeline_tag: text-generation library_name: transformers

Details

This model is a merge between Trappu/Nemo-Picaro-12B, a model trained on my own little dataset free of synthetic data, which focuses solely on storywriting and scenrio prompting (Example: [ Scenario: bla bla bla; Tags: bla bla bla ]), and anthracite-org/magnum-v2-12b.

The reason why I decided to merge it with Magnum (and don't recommend Picaro alone) is because that model, aside from its obvious flaws (rampant impersonation, stupid, etc...), is a one-trick pony and will be really rough for the average LLM user to handle. The idea was to have Magnum work as some sort of stabilizer to fix the issues that emerge from the lack of multiturn/smart data in Picaro's dataset. It worked, I think. I enjoy the outputs and it's smart enough to work with.

But yeah the goal of this merge was to make a model that's both good at storytelling/narration but also fine when it comes to other forms of creative writing such as RP or chatting. I don't think it's quite there yet but it's something for sure.

Prompting

As explained before, Picaro is a model that functions mainly through scenario prompting but merging it with Magnum has made it a lot more versatile so you can use it however you see fit. Both models were trained on chatml so below is the recommended prompt formatting.

<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
bla bla bla<|im_end|>
<|im_start|>assistant
bla bla bla you!<|im_end|>

For SillyTavern users:

Instruct template

Context template

Settings preset

The above settings are the ones I recommend.

Temp = 1.2

Min P = 0.1

DRY Rep Pen: Multiplier = 0.8, Base = 1.75, Allowed Length = 2, Penalty Range = 1024

Little guide on useful samplers and how to import settings presets and instruct/context templates and other stuff people might find useful here

Every other sampler neutralized.

Quants

Imatrix: https://huggingface.co/mradermacher/Magnum-Picaro-0.7-v2-12b-i1-GGUF

Static: https://huggingface.co/mradermacher/Magnum-Picaro-0.7-v2-12b-GGUF

Magnum-Picaro-0.7-v2-12b

Magnum-Picaro-0.7-v2-12b is a merge of the following models using LazyMergekit:

🧩 Configuration

yaml

models:
    - model: Trappu/Nemo-Picaro-12B
      parameters:
        density: 0.7
        weight: 0.5
    - model: anthracite-org/magnum-v2-12b
      parameters:
        density: 0.3
        weight: 0.5

merge_method: ties
base_model: Trappu/Nemo-Picaro-12B
parameters:
    normalize: true
    int8_mask: true
dtype: bfloat16

💻 Usage

python

!pip install -qU transformers accelerate

from transformers import AutoTokenizer
import transformers
import torch

model = "Trappu/Magnum-Picaro-0.7-v2-12b"
messages = [{"role": "user", "content": "What is a large language model?"}]

tokenizer = AutoTokenizer.from_pretrained(model)
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)

outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	21.42
IFEval (0-Shot)	30.03
BBH (3-Shot)	35.75
MATH Lvl 5 (4-Shot)	4.76
GPQA (0-shot)	9.73
MuSR (0-shot)	19.56
MMLU-PRO (5-shot)	28.67

RichardErkhov/Trappu_-_Magnum-Picaro-0.7-v2-12b-gguf