You can deploy this model and start earning money today!

RichardErkhov/
vonjack_-_SmolLM2-1.7B-Merged-gguf

Name: vonjack_-_SmolLM2-1.7B-Merged-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

SmolLM2-1.7B-Merged - GGUF

Model creator: https://huggingface.co/vonjack/
Original model: https://huggingface.co/vonjack/SmolLM2-1.7B-Merged/

Name	Quant method	Size
SmolLM2-1.7B-Merged.Q2_K.gguf	Q2_K	0.63GB
SmolLM2-1.7B-Merged.IQ3_XS.gguf	IQ3_XS	0.69GB
SmolLM2-1.7B-Merged.IQ3_S.gguf	IQ3_S	0.72GB
SmolLM2-1.7B-Merged.Q3_K_S.gguf	Q3_K_S	0.72GB
SmolLM2-1.7B-Merged.IQ3_M.gguf	IQ3_M	0.75GB
SmolLM2-1.7B-Merged.Q3_K.gguf	Q3_K	0.8GB
SmolLM2-1.7B-Merged.Q3_K_M.gguf	Q3_K_M	0.8GB
SmolLM2-1.7B-Merged.Q3_K_L.gguf	Q3_K_L	0.87GB
SmolLM2-1.7B-Merged.IQ4_XS.gguf	IQ4_XS	0.88GB
SmolLM2-1.7B-Merged.Q4_0.gguf	Q4_0	0.92GB
SmolLM2-1.7B-Merged.IQ4_NL.gguf	IQ4_NL	0.93GB
SmolLM2-1.7B-Merged.Q4_K_S.gguf	Q4_K_S	0.93GB
SmolLM2-1.7B-Merged.Q4_K.gguf	Q4_K	0.98GB
SmolLM2-1.7B-Merged.Q4_K_M.gguf	Q4_K_M	0.98GB
SmolLM2-1.7B-Merged.Q4_1.gguf	Q4_1	1.02GB
SmolLM2-1.7B-Merged.Q5_0.gguf	Q5_0	1.11GB
SmolLM2-1.7B-Merged.Q5_K_S.gguf	Q5_K_S	1.11GB
SmolLM2-1.7B-Merged.Q5_K.gguf	Q5_K	1.14GB
SmolLM2-1.7B-Merged.Q5_K_M.gguf	Q5_K_M	1.14GB
SmolLM2-1.7B-Merged.Q5_1.gguf	Q5_1	1.2GB
SmolLM2-1.7B-Merged.Q6_K.gguf	Q6_K	1.31GB
SmolLM2-1.7B-Merged.Q8_0.gguf	Q8_0	1.7GB

Original model description:

base_model:

HuggingFaceTB/SmolLM2-1.7B
HuggingFaceTB/SmolLM2-1.7B-Instruct library_name: transformers tags:
mergekit
merge

SmolLM2-1.7B-Merged

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using HuggingFaceTB/SmolLM2-1.7B as a base.

Models Merged

The following models were included in the merge:

HuggingFaceTB/SmolLM2-1.7B-Instruct

Configuration

The following YAML configuration was used to produce this model:

yaml

models:
  - model: HuggingFaceTB/SmolLM2-1.7B-Instruct
    parameters:
      weight: 1
merge_method: ties
base_model: HuggingFaceTB/SmolLM2-1.7B
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

RichardErkhov/vonjack_-_SmolLM2-1.7B-Merged-gguf