miquliz-120b-GGUF

• EXL2: 2.4bpw | 2.65bpw | 2.9bpw | 4.0bpw
• GGUF: IQ3_XXS | Q4_K_S+Q4_K_M
• HF: wolfram/miquliz-120b

This is a 120b frankenmerge created by interleaving layers of miqu-1-70b-sf with lzlv_70b_fp16_hf using mergekit.

Inspired by goliath-120b.

Thanks for the support, CopilotKit - the open-source platform for building in-app AI Copilots into any product, with any LLM model. Check out their GitHub.

Thanks for the EXL2 and GGUF quants, Lone Striker and NanoByte!

Prompt template: Mistral

<s>[INST] {prompt} [/INST]

See also: 🐺🐦‍⬛ LLM Prompt Format Comparison/Test: Mixtral 8x7B Instruct with 17 different instruct templates : LocalLLaMA

Model Details

• Max Context: 32768 tokens
• Layers: 137

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

• 152334H/miqu-1-70b-sf
• lizpreciatior/lzlv_70b_fp16_hf

Configuration

The following YAML configuration was used to produce this model:

dtype: float16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 16]
    model: 152334H/miqu-1-70b-sf
- sources:
  - layer_range: [8, 24]
    model: lizpreciatior/lzlv_70b_fp16_hf
- sources:
  - layer_range: [17, 32]
    model: 152334H/miqu-1-70b-sf
- sources:
  - layer_range: [25, 40]
    model: lizpreciatior/lzlv_70b_fp16_hf
- sources:
  - layer_range: [33, 48]
    model: 152334H/miqu-1-70b-sf
- sources:
  - layer_range: [41, 56]
    model: lizpreciatior/lzlv_70b_fp16_hf
- sources:
  - layer_range: [49, 64]
    model: 152334H/miqu-1-70b-sf
- sources:
  - layer_range: [57, 72]
    model: lizpreciatior/lzlv_70b_fp16_hf
- sources:
  - layer_range: [65, 80]
    model: 152334H/miqu-1-70b-sf

Credits & Special Thanks

• 1st model:
  • original (unreleased) model: mistralai (Mistral AI_)
  • leaked model: miqudev/miqu-1-70b
  • f16 model: 152334H/miqu-1-70b-sf
• 2nd model: lizpreciatior/lzlv_70b_fp16_hf
• mergekit: arcee-ai/mergekit: Tools for merging pretrained large language models.
• mergekit_config.yml: alpindale/goliath-120b
• gguf quantization: ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++

Support

• My Ko-fi page if you'd like to tip me to say thanks or request specific models to be tested or merged with priority. Also consider supporting your favorite model creators, quantizers, or frontend/backend devs if you can afford to do so. They deserve it!

DISCLAIMER: THIS IS BASED ON A LEAKED ASSET AND HAS NO LICENSE ASSOCIATED WITH IT. USE AT YOUR OWN RISK.