Configuration Parsing
Warning:
In config.json: "quantization_config.bits" must be an integer
merged_model
This is a merge of pre-trained language models created using mergekit.
Merge Details
Merge Method
This model was merged using the passthrough merge method.
Models Merged
The following models were included in the merge:
Configuration
The following YAML configuration was used to produce this model:
slices:
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [0, 12]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [6, 18]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [12, 24]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [18, 30]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [24, 36]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [30, 42]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [36, 48]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [42, 54]
- sources:
- model: 01-ai/Yi-1.5-34B-Chat-16K
layer_range: [48, 60]
merge_method: passthrough
dtype: float16
- Downloads last month
- 4
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for denru/Yi-1.5-34B-Chat-16Kx2-4_65bpw-h8-exl2-pippa
Base model
01-ai/Yi-1.5-34B-Chat-16K
Quantized
this model