CoolFace
Modelpublic

RichardErkhov/Manirajan_-_interview_qwen2_1.5b2-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes343downloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

interviewqwen21.5b2 - GGUF

  • —Model creator: https://huggingface.co/Manirajan/
  • —Original model: https://huggingface.co/Manirajan/interviewqwen21.5b2/
NameQuant methodSize
interview_qwen2_1.5b2.Q2_K.ggufQ2_K0.63GB
interview_qwen2_1.5b2.IQ3_XS.ggufIQ3_XS0.68GB
interview_qwen2_1.5b2.IQ3_S.ggufIQ3_S0.71GB
interview_qwen2_1.5b2.Q3_K_S.ggufQ3KS0.71GB
interview_qwen2_1.5b2.IQ3_M.ggufIQ3_M0.72GB
interview_qwen2_1.5b2.Q3_K.ggufQ3_K0.77GB
interview_qwen2_1.5b2.Q3_K_M.ggufQ3KM0.77GB
interview_qwen2_1.5b2.Q3_K_L.ggufQ3KL0.82GB
interview_qwen2_1.5b2.IQ4_XS.ggufIQ4_XS0.84GB
interview_qwen2_1.5b2.Q4_0.ggufQ4_00.87GB
interview_qwen2_1.5b2.IQ4_NL.ggufIQ4_NL0.88GB
interview_qwen2_1.5b2.Q4_K_S.ggufQ4KS0.88GB
interview_qwen2_1.5b2.Q4_K.ggufQ4_K0.92GB
interview_qwen2_1.5b2.Q4_K_M.ggufQ4KM0.92GB
interview_qwen2_1.5b2.Q4_1.ggufQ4_10.95GB
interview_qwen2_1.5b2.Q5_0.ggufQ5_01.02GB
interview_qwen2_1.5b2.Q5_K_S.ggufQ5KS1.02GB
interview_qwen2_1.5b2.Q5_K.ggufQ5_K1.05GB
interview_qwen2_1.5b2.Q5_K_M.ggufQ5KM1.05GB
interview_qwen2_1.5b2.Q5_1.ggufQ5_11.1GB
interview_qwen2_1.5b2.Q6_K.ggufQ6_K1.19GB
interview_qwen2_1.5b2.Q8_0.ggufQ8_01.53GB

Original model description: --- base_model: unsloth/Qwen2-1.5B language:

  • —en license: apache-2.0 tags:
  • —text-generation-inference
  • —transformers
  • —unsloth
  • —qwen2
  • —trl
  • —sft ---

Uploaded model

  • —Developed by: Manirajan
  • —License: apache-2.0
  • —Finetuned from model : unsloth/Qwen2-1.5B

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>