You can deploy this model and start earning money today!

RichardErkhov/
MrOvkill_-_Phi-3-Instruct-Bloated-gguf

Name: MrOvkill_-_Phi-3-Instruct-Bloated-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Phi-3-Instruct-Bloated - GGUF

Model creator: https://huggingface.co/MrOvkill/
Original model: https://huggingface.co/MrOvkill/Phi-3-Instruct-Bloated/

Name	Quant method	Size
Phi-3-Instruct-Bloated.Q2_K.gguf	Q2_K	1.32GB
Phi-3-Instruct-Bloated.IQ3_XS.gguf	IQ3_XS	1.51GB
Phi-3-Instruct-Bloated.IQ3_S.gguf	IQ3_S	1.57GB
Phi-3-Instruct-Bloated.Q3_K_S.gguf	Q3_K_S	1.57GB
Phi-3-Instruct-Bloated.IQ3_M.gguf	IQ3_M	1.73GB
Phi-3-Instruct-Bloated.Q3_K.gguf	Q3_K	1.82GB
Phi-3-Instruct-Bloated.Q3_K_M.gguf	Q3_K_M	1.82GB
Phi-3-Instruct-Bloated.Q3_K_L.gguf	Q3_K_L	1.94GB
Phi-3-Instruct-Bloated.IQ4_XS.gguf	IQ4_XS	1.93GB
Phi-3-Instruct-Bloated.Q4_0.gguf	Q4_0	2.03GB
Phi-3-Instruct-Bloated.IQ4_NL.gguf	IQ4_NL	2.04GB
Phi-3-Instruct-Bloated.Q4_K_S.gguf	Q4_K_S	2.04GB
Phi-3-Instruct-Bloated.Q4_K.gguf	Q4_K	2.23GB
Phi-3-Instruct-Bloated.Q4_K_M.gguf	Q4_K_M	2.23GB
Phi-3-Instruct-Bloated.Q4_1.gguf	Q4_1	2.24GB
Phi-3-Instruct-Bloated.Q5_0.gguf	Q5_0	2.46GB
Phi-3-Instruct-Bloated.Q5_K_S.gguf	Q5_K_S	2.46GB
Phi-3-Instruct-Bloated.Q5_K.gguf	Q5_K	2.62GB
Phi-3-Instruct-Bloated.Q5_K_M.gguf	Q5_K_M	2.62GB
Phi-3-Instruct-Bloated.Q5_1.gguf	Q5_1	2.68GB
Phi-3-Instruct-Bloated.Q6_K.gguf	Q6_K	2.92GB
Phi-3-Instruct-Bloated.Q8_0.gguf	Q8_0	3.78GB

Original model description:

tags:

merge
mergekit
lazymergekit
microsoft/Phi-3-mini-128k-instruct
NexaAIDev/Octopus-v4 base_model:
microsoft/Phi-3-mini-128k-instruct
NexaAIDev/Octopus-v4 license: mit language:
en library_name: transformers pipeline_tag: text-generation

Phi-3-Instruct-Bloated

Phi-3-Instruct-Bloated is a merge of the following models using LazyMergekit:

🧩 Configuration

yaml

slices:
  - sources:
      - model: microsoft/Phi-3-mini-128k-instruct
        layer_range: [0, 32]
      - model: NexaAIDev/Octopus-v4
        layer_range: [0, 32]
merge_method: slerp
base_model: microsoft/Phi-3-mini-128k-instruct
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16

💻 Usage

python

# Installation
!pip install -qU transformers accelerate

# Imports
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# Loading
tokenizer = AutoTokenizer.from_pretrained("MrOvkill/Phi-3-Instruct-Bloated")
model = AutoModelForCausalLM.from_pretrained("MrOvkill/Phi-3-Instruct-Bloated")

# Completion function
def infer(prompt, **kwargs):
    inputs = tokenizer(prompt, return_tensors="pt")
    with torch.no_grad():
        outputs = model.generate(**inputs, **kwargs)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Some silliness
infer("<|user|>\nBen is going to the store for some Ice Cream. So is Jerry. They mix up the ice cream at the store. Is the ice cream: (a. Ben's (b. Jerry's (c. Ben and Jerry's <|end|>\n<|assistant|>\nMy answer is (", max_new_tokens=1024)

# A proper test
infer(
    """
<|user|>
Explain what a Mixture of Experts is in less than 100 words.
<|assistant|>
""",
    max_new_tokens=1024,
    do_sample=False,
    temperature=0.0,
    top_k=50,
    top_p=0.89,
)

RichardErkhov/MrOvkill_-_Phi-3-Instruct-Bloated-gguf

Original model description:

Phi-3-Instruct-Bloated

🧩 Configuration

💻 Usage

RichardErkhov/
MrOvkill_-_Phi-3-Instruct-Bloated-gguf