Neo_7b-merge8 / mergekit_config.yml
DewEfresh's picture
Upload folder using huggingface_hub
a07e925 verified
raw
history blame contribute delete
No virus
3.67 kB
slices:
# Group 1 (layers 0-3 to 0-2)
- sources:
- model: m-a-p/neo_7b
layer_range: [0, 0]
- model: DewEfresh/neo_7b
layer_range: [3, 3]
- sources:
- model: m-a-p/neo_7b
layer_range: [1, 1]
- model: DewEfresh/neo_7b
layer_range: [3, 3]
- sources:
- model: m-a-p/neo_7b
layer_range: [2, 2]
- model: DewEfresh/neo_7b
layer_range: [3, 3]
# Group 2 (layers 4-7 to 3-5)
- sources:
- model: m-a-p/neo_7b
layer_range: [3, 3]
- model: DewEfresh/neo_7b
layer_range: [7, 7]
- sources:
- model: m-a-p/neo_7b
layer_range: [4, 4]
- model: DewEfresh/neo_7b
layer_range: [7, 7]
- sources:
- model: m-a-p/neo_7b
layer_range: [5, 5]
- model: DewEfresh/neo_7b
layer_range: [7, 7]
# Group 3 (layers 8-11 to 6-8)
- sources:
- model: m-a-p/neo_7b
layer_range: [6, 6]
- model: DewEfresh/neo_7b
layer_range: [11, 11]
- sources:
- model: m-a-p/neo_7b
layer_range: [7, 7]
- model: DewEfresh/neo_7b
layer_range: [11, 11]
- sources:
- model: m-a-p/neo_7b
layer_range: [8, 8]
- model: DewEfresh/neo_7b
layer_range: [11, 11]
# Group 4 (layers 12-15 to 9-11)
- sources:
- model: m-a-p/neo_7b
layer_range: [9, 9]
- model: DewEfresh/neo_7b
layer_range: [15, 15]
- sources:
- model: m-a-p/neo_7b
layer_range: [10, 10]
- model: DewEfresh/neo_7b
layer_range: [15, 15]
- sources:
- model: m-a-p/neo_7b
layer_range: [11, 11]
- model: DewEfresh/neo_7b
layer_range: [15, 15]
# Group 5 (layers 16-19 to 12-14)
- sources:
- model: m-a-p/neo_7b
layer_range: [12, 12]
- model: DewEfresh/neo_7b
layer_range: [19, 19]
- sources:
- model: m-a-p/neo_7b
layer_range: [13, 13]
- model: DewEfresh/neo_7b
layer_range: [19, 19]
- sources:
- model: m-a-p/neo_7b
layer_range: [14, 14]
- model: DewEfresh/neo_7b
layer_range: [19, 19]
# Group 6 (layers 20-23 to 15-17)
- sources:
- model: m-a-p/neo_7b
layer_range: [15, 15]
- model: DewEfresh/neo_7b
layer_range: [23, 23]
- sources:
- model: m-a-p/neo_7b
layer_range: [16, 16]
- model: DewEfresh/neo_7b
layer_range: [23, 23]
- sources:
- model: m-a-p/neo_7b
layer_range: [17, 17]
- model: DewEfresh/neo_7b
layer_range: [23, 23]
# Group 7 (layers 24-27 to 18-20)
- sources:
- model: m-a-p/neo_7b
layer_range: [18, 18]
- model: DewEfresh/neo_7b
layer_range: [27, 27]
- sources:
- model: m-a-p/neo_7b
layer_range: [19, 19]
- model: DewEfresh/neo_7b
layer_range: [27, 27]
- sources:
- model: m-a-p/neo_7b
layer_range: [20, 20]
- model: DewEfresh/neo_7b
layer_range: [27, 27]
merge_method: slerp
base_model: m-a-p/neo_7b
parameters:
t:
- 0.75 # Weight for m-a-p/neo_7b layer
- 0.25 # Weight for the 4th DewEfresh/neo_7b layer being merged
dtype: bfloat16
output_path: ./merged_reduced_map_dewefresh_neo_7b
model_config:
architectures: ["LlamaForCausalLM"]
attention_bias: false
attention_dropout: 0.0
hidden_act: "silu"
hidden_size: 3072
intermediate_size: 24576
max_position_embeddings: 8192
model_type: "llama"
num_attention_heads: 16
num_hidden_layers: 21 # Reduced from 28 to 21
num_key_value_heads: 16
rms_norm_eps: 1e-05
rope_theta: 10000.0
use_cache: true
vocab_size: 64256