vince62s/phi-2-psy-GGUF

Quantized GGUF model files for phi-2-psy from vince62s

Name	Quant method	Size
phi-2-psy.fp16.gguf	fp16	5.56 GB
phi-2-psy.q2_k.gguf	q2_k	1.11 GB
phi-2-psy.q3_k_m.gguf	q3_k_m	1.43 GB
phi-2-psy.q4_k_m.gguf	q4_k_m	1.74 GB
phi-2-psy.q5_k_m.gguf	q5_k_m	2.00 GB
phi-2-psy.q6_k.gguf	q6_k	2.29 GB
phi-2-psy.q8_0.gguf	q8_0	2.96 GB

Original Model Card:

Phi-2-psy

Phi-2-psy is a merge of the following models:

• rhysjones/phi-2-orange
• cognitivecomputations/dolphin-2_6-phi-2

🏆 Evaluation

The evaluation was performed using LLM AutoEval on Nous suite.

Model	AGIEval	GPT4All	TruthfulQA	Bigbench	Average
phi-2-psy	34.4	71.4	48.2	38.1	48.02
phixtral-2x2_8	34.1	70.4	48.8	37.8	47.78
dolphin-2_6-phi-2	33.1	69.9	47.4	37.2	46.89
phi-2-orange	33.4	71.3	49.9	37.3	47.97
phi-2	28.0	70.8	44.4	35.2	44.61

🧩 Configuration

slices:
  - sources:
      - model: rhysjones/phi-2-orange
        layer_range: [0, 32]
      - model: cognitivecomputations/dolphin-2_6-phi-2
        layer_range: [0, 32]
merge_method: slerp
base_model: rhysjones/phi-2-orange
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

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
torch.set_default_device("cuda")
model = AutoModelForCausalLM.from_pretrained("vince62s/phi-2-psy", torch_dtype="auto", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("vince62s/phi-2-psy", trust_remote_code=True)
inputs = tokenizer('''def print_prime(n):
   """
   Print all primes between 1 and n
   """''', return_tensors="pt", return_attention_mask=False)
outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)