Quantization made by Richard Erkhov.

TinyLlama_1.1b_test - GGUF

Model creator: https://huggingface.co/Kame1024/
Original model: https://huggingface.co/Kame1024/TinyLlama_1.1b_test/

Name	Quant method	Size
TinyLlama_1.1b_test.Q2_K.gguf	Q2_K	0.4GB
TinyLlama_1.1b_test.IQ3_XS.gguf	IQ3_XS	0.44GB
TinyLlama_1.1b_test.IQ3_S.gguf	IQ3_S	0.47GB
TinyLlama_1.1b_test.Q3_K_S.gguf	Q3_K_S	0.47GB
TinyLlama_1.1b_test.IQ3_M.gguf	IQ3_M	0.48GB
TinyLlama_1.1b_test.Q3_K.gguf	Q3_K	0.51GB
TinyLlama_1.1b_test.Q3_K_M.gguf	Q3_K_M	0.51GB
TinyLlama_1.1b_test.Q3_K_L.gguf	Q3_K_L	0.55GB
TinyLlama_1.1b_test.IQ4_XS.gguf	IQ4_XS	0.57GB
TinyLlama_1.1b_test.Q4_0.gguf	Q4_0	0.59GB
TinyLlama_1.1b_test.IQ4_NL.gguf	IQ4_NL	0.6GB
TinyLlama_1.1b_test.Q4_K_S.gguf	Q4_K_S	0.6GB
TinyLlama_1.1b_test.Q4_K.gguf	Q4_K	0.62GB
TinyLlama_1.1b_test.Q4_K_M.gguf	Q4_K_M	0.62GB
TinyLlama_1.1b_test.Q4_1.gguf	Q4_1	0.65GB
TinyLlama_1.1b_test.Q5_0.gguf	Q5_0	0.71GB
TinyLlama_1.1b_test.Q5_K_S.gguf	Q5_K_S	0.71GB
TinyLlama_1.1b_test.Q5_K.gguf	Q5_K	0.73GB
TinyLlama_1.1b_test.Q5_K_M.gguf	Q5_K_M	0.73GB
TinyLlama_1.1b_test.Q5_1.gguf	Q5_1	0.77GB
TinyLlama_1.1b_test.Q6_K.gguf	Q6_K	0.84GB
TinyLlama_1.1b_test.Q8_0.gguf	Q8_0	1.09GB

Original model description:

base_model: - TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T - TinyLlama/TinyLlama-1.1B-Chat-v1.0 library_name: transformers tags: - mergekit - merge inference: parameters: temperature: 0.0 widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits?

storage

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

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


models:
  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
    parameters:
      weight: 1.0
  - model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
    parameters:
      weight: 1.0
merge_method: linear
dtype: float16