The Kaitchup

company

https://kaitchup.substack.com/

bnjmn_marie

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

bnjmnmarie updated a collection about 22 hours ago

Quantized VibeThinker-1.5B

bnjmnmarie updated a collection about 22 hours ago

Quantized VibeThinker-1.5B

bnjmnmarie updated a collection about 22 hours ago

Quantized VibeThinker-1.5B

View all activity

kaitchup 's collections 30

Quantized VibeThinker-1.5B

Verified models. Tested with vLLM.

kaitchup/VibeThinker-1.5B-w8a8-smoothquant

2B • Updated about 22 hours ago • 9
kaitchup/VibeThinker-1.5B-awq-w4a16-asym

0.6B • Updated about 22 hours ago • 6
kaitchup/VibeThinker-1.5B-fp8-dynamic

2B • Updated about 22 hours ago • 13
kaitchup/VibeThinker-1.5B-gptq-w4a16-g128

0.7B • Updated about 22 hours ago • 6

Compressed Tensors Demo

kaitchup/Qwen3-4B-Instruct-2507-gptq-w4a16-g128

1B • Updated 24 days ago • 12
kaitchup/Qwen3-4B-Instruct-2507-NVFP4

3B • Updated 24 days ago • 16
kaitchup/Qwen3-4B-Instruct-2507-autoround-w4a16-g128

1B • Updated 23 days ago • 8
kaitchup/Qwen3-4B-Instruct-2507-fp8-dynamic

4B • Updated 24 days ago • 11

NVFP4

LLMs quantized with LLM Compressor to NVFP4. Check the JSON files in the model directories for more information.

kaitchup/Qwen3-0.6B-NVFP4

0.6B • Updated Sep 8 • 25
kaitchup/Qwen3-4B-NVFP4

3B • Updated Sep 8 • 104
kaitchup/Qwen3-1.7B-NVFP4

1B • Updated Sep 8 • 7
kaitchup/Qwen3-8B-NVFP4

5B • Updated Sep 8 • 38 • 1

Quantized Qwen3

kaitchup/Qwen3-32B-autoround-2bit-gptq

5B • Updated May 2 • 10 • 1
kaitchup/Qwen3-32B-autoround-4bit-gptq

6B • Updated May 2 • 49 • 4
kaitchup/Qwen3-1.7B-autoround-4bit-gptq

0.5B • Updated May 2 • 10
kaitchup/Qwen3-4B-autoround-4bit-gptq

0.9B • Updated May 2 • 43 • 1

Quantized QwQ 32B

kaitchup/QwQ-32B-bnb-4bit

Text Generation • 18B • Updated Mar 7 • 9 • 1
kaitchup/QwQ-32B-AutoRoundGPTQ-8bit

Text Generation • 10B • Updated Mar 7 • 53 • 2
kaitchup/QwQ-32B-AutoRoundGPTQ-4bit

Text Generation • 6B • Updated Mar 7 • 6 • 1
kaitchup/QwQ-32B-AutoRoundGPTQ-3bit

Text Generation • 5B • Updated Mar 7 • 13

Quantized Mistral Small 3

kaitchup/Mistral-Small-24B-Instruct-2501-AutoRound-GPTQ-4bit

4B • Updated Feb 4 • 89 • 1
kaitchup/Mistral-Small-24B-Base-2501-AutoRound-GPTQ-4bit

4B • Updated Feb 4 • 6

Quantized QwQ

kaitchup/QwQ-32B-Preview-AutoRound-GPTQ-2bit

Text Generation • 4B • Updated Dec 31, 2024 • 9 • 2
kaitchup/QwQ-32B-Preview-AutoRound-GPTQ-4bit

Text Generation • 6B • Updated Dec 29, 2024 • 5

Quantized Llama 3.3

kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 11B • Updated Dec 9, 2024 • 321 • 6

Quantized Tulu 3 and OLMo 2

kaitchup/OLMo-2-1124-7B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Nov 28, 2024 • 7 • 1
kaitchup/Llama-3.1-Tulu-3-70B-AutoRound-GPTQ-4bit

Text Generation • 11B • Updated Nov 28, 2024 • 6
kaitchup/Llama-3.1-Tulu-3-8B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Nov 28, 2024 • 2
kaitchup/OLMo-2-1124-13B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 3B • Updated Nov 28, 2024 • 9

Opus Translation Datasets

Some language pairs of OPUS formatted to have source and target sentences as single sequences. Intended to facilitate fine-tuning of causal LLMs.

kaitchup/opus-Vietnamese-to-English

Viewer • Updated Nov 1, 2023 • 994k • 91 • 1
kaitchup/opus-Indonesian-to-English

Viewer • Updated Nov 1, 2023 • 992k • 123 • 4
kaitchup/opus-Norwegian-to-English

Viewer • Updated Nov 1, 2023 • 1M • 70 • 1
kaitchup/opus-Dutch-to-English

Viewer • Updated Nov 1, 2023 • 972k • 77 • 1

GPTQ

Llama 2 7B, 13B, Llama 3 8B, and Mistral 7B quantized with GPTQ in 2-bit, 3-bit, 4-bit and 8-bit with GPTQ.

kaitchup/Llama-2-7b-hf-gptq-8bit

Text Generation • 2B • Updated Jan 19, 2024 • 8
kaitchup/Llama-2-7b-hf-gptq-3bit

Text Generation • 0.9B • Updated Jan 20, 2024 • 957 • 1
kaitchup/Llama-2-7b-hf-gptq-2bit

Text Generation • 0.7B • Updated Jan 20, 2024 • 948
kaitchup/Llama-2-7b-hf-gptq-4bit

Text Generation • 1B • Updated Jan 19, 2024 • 8

Contaminated Mistral 7B and TinyLlama

Contaminated Mistral 7B and TinyLlama adapters, and the datasets used for contamination.

kaitchup/Mistral-7B-v0.1-contaminated-e1

Updated Mar 21, 2024
kaitchup/Mistral-7B-v0.1-contaminated-e5

Updated Mar 21, 2024
kaitchup/TinyLlama-1.1B-intermediate-step-1431k-3T-contaminated-e1

Updated Mar 21, 2024
kaitchup/TinyLlama-1.1B-intermediate-step-1431k-3T-contaminated-e5

Updated Mar 21, 2024

Llama 3 70B ExLlamaV2 (bpw: 4.0, 3.5, 3.0, 2.5, and 2.18)

kaitchup/Llama-3-70B-3.5bpw-exl2

Text Generation • Updated May 5, 2024 • 8
kaitchup/Llama-3-70B-3.0bpw-exl2

Text Generation • Updated May 5, 2024 • 5
kaitchup/Llama-3-70B-2.5bpw-exl2

Text Generation • Updated May 5, 2024 • 8
kaitchup/Llama-3-70B-2.18bpw-exl2

Text Generation • Updated May 5, 2024 • 5

[Basics] AutoRound: Llama 3

kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ

Text Generation • 2B • Updated Jun 28, 2024
kaitchup/Llama-3-8B-4bit-Symm-AutoRound-GPTQ

Text Generation • 2B • Updated Jun 28, 2024

The Minitron Models and Their Teachers, Quantized

kaitchup/Mistral-NeMo-Minitron-8B-Base-AutoRound-GPTQ-sym-4bit

Text Generation • 2B • Updated Aug 27, 2024 • 5
kaitchup/Mistral-NeMo-Minitron-8B-Base-AutoRound-GPTQ-asym-4bit

Text Generation • 2B • Updated Aug 26, 2024 • 7
kaitchup/Mistral-Nemo-Base-2407-AutoRound-GPTQ-asym-4bit

Text Generation • 3B • Updated Aug 26, 2024 • 10
kaitchup/Llama-3.1-Minitron-4B-Width-Base-AutoRound-GPTQ-asym-4bit

Text Generation • 1B • Updated Aug 26, 2024 • 3

Quantized Olmo 3

Verified models.

kaitchup/Olmo-3-7B-Instruct-fp8-dynamic

7B • Updated 11 days ago • 33
kaitchup/Olmo-3-7B-Instruct-gptq-w4a16-g128

2B • Updated 11 days ago • 26
kaitchup/Olmo-3-7B-Instruct-NVFP4

4B • Updated 16 days ago • 123
kaitchup/Olmo-3-7B-Instruct-w8a8-smoothquant

7B • Updated 8 days ago • 66

Quantized Qwen3-VL

kaitchup/Qwen3-VL-2B-Instruct-NVFP4

2B • Updated Nov 5 • 9
kaitchup/Qwen3-VL-8B-Instruct-NVFP4

2B • Updated Nov 5 • 24
kaitchup/Qwen3-VL-2B-Instruct-W4A16

0.9B • Updated Nov 5 • 22 • 2
kaitchup/Qwen3-VL-8B-Instruct-W4A16

2B • Updated Nov 5 • 25

EoRA Adapters for Qwen2.5 and Qwen3

kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq-EoRA-r32

Updated May 12
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq-EoRA-r64

Updated May 12
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq-EoRA-r256

Updated May 12
kaitchup/Qwen3-32B-autoround-2bit-128g-gptq-EoRA-r64

Updated May 13

2-bit Qwen2.5 72B Instruct

kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq

9B • Updated May 7 • 6
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-128g-4096-gptq

7B • Updated May 7 • 7
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-128g-2048-gptq

7B • Updated May 7 • 5
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-64g-4096-gptq

8B • Updated May 7 • 8

Quantized Phi-4 Mini

kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-8bit

Text Generation • 1B • Updated Feb 28 • 81
kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-3bit

Text Generation • 0.9B • Updated Feb 28 • 8
kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-4bit

Text Generation • 1B • Updated Feb 28 • 55
kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-2bit

Text Generation • 0.9B • Updated Feb 28 • 13

Quantized DeepSeek R1 Distill

kaitchup/DeepSeek-R1-Distill-Llama-8B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Jan 27 • 412 • 1
kaitchup/DeepSeek-R1-Distill-Qwen-14B-AutoRound-GPTQ-4bit

Text Generation • 3B • Updated Jan 27 • 77 • 7
kaitchup/DeepSeek-R1-Distill-Qwen-7B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Jan 27 • 6 • 2

Quantized Falcon3

kaitchup/Falcon3-10B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 31, 2024 • 9
kaitchup/Falcon3-10B-Base-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 19, 2024 • 8
kaitchup/Falcon3-7B-Base-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 19, 2024 • 4
kaitchup/Falcon3-7B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 19, 2024 • 8

Quantized EuroLLM

kaitchup/EuroLLM-9B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 6, 2024 • 9
kaitchup/EuroLLM-9B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 6, 2024 • 7 • 1

Quantized Qwen2.5

kaitchup/Qwen2.5-1.5B-AutoRound-GPTQ-asym-4bit

Text Generation • 0.4B • Updated Oct 18, 2024 • 9
kaitchup/Qwen2.5-7B-AutoRound-GPTQ-asym-4bit

Text Generation • 2B • Updated Oct 18, 2024 • 3
kaitchup/Qwen2.5-1.5B-Instruct-AutoRound-GPTQ-asym-4bit

Text Generation • 0.4B • Updated Oct 18, 2024 • 9
kaitchup/Qwen2.5-7B-Instruct-AutoRound-GPTQ-asym-4bit

Text Generation • 2B • Updated Oct 18, 2024 • 7

Llama 2 7B MT

Machine translation adapters for Llama 2 7B.

kaitchup/Llama-2-7b-mt-French-to-English

Translation • Updated Nov 2, 2023 • 113 • 3
kaitchup/Llama-2-7b-mt-Italian-to-English

Translation • Updated Nov 2, 2023 • 7
kaitchup/Llama-2-7b-mt-Indonesian-to-English

Translation • Updated Nov 2, 2023 • 13
kaitchup/Llama-2-7b-mt-Vietnamese-to-English

Translation • Updated Nov 2, 2023 • 6

Quantized and fine-tuned versions of the Yi models

kaitchup/Yi-6B-gptq-4bit

Text Generation • 1B • Updated Mar 21, 2024 • 11
kaitchup/Yi-6B-awq-4bit

Text Generation • 1B • Updated Mar 21, 2024 • 9
kaitchup/Yi-6B-bnb-4bit

Text Generation • 3B • Updated Mar 21, 2024 • 11
kaitchup/Yi-6B-openguanaco-3e-QLoRA

Updated Mar 21, 2024

The Mayonnaise

A collection of 7B models made with mergekit.

kaitchup/Mayonnaise-4in1-03

Text Generation • 7B • Updated Mar 17, 2024 • 62 • 2
kaitchup/Mayonnaise-4in1-01

Text Generation • 7B • Updated Mar 17, 2024 • 66 • 1
kaitchup/Mayonnaise-4in1-02

Text Generation • 7B • Updated Apr 10, 2024 • 78
kaitchup/TheMayonnaise

Text Generation • 7B • Updated Mar 17, 2024 • 59 • 1

[Basics] Quantized Phi-3

kaitchup/Phi-3-mini-4k-instruct-gptq-4bit

Text Generation • 0.7B • Updated Apr 25, 2024 • 899k • 2
kaitchup/Phi-3-medium-128k-instruct-awq-4bit

Text Generation • 2B • Updated Jun 21, 2024 • 1
kaitchup/Phi-3-mini-4k-instruct-bnb-4bit

Text Generation • 2B • Updated Apr 25, 2024 • 9
kaitchup/Phi-3-medium-4k-instruct-awq-4bit

Text Generation • 2B • Updated Jun 21, 2024 • 1

Quantized Llama 3.1

kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-sym

Text Generation • 2B • Updated Aug 13, 2024 • 5 • 1
kaitchup/Meta-Llama-3.1-8B-Instruct-awq-4bit

Text Generation • 2B • Updated Aug 13, 2024 • 21 • 1
kaitchup/Meta-Llama-3.1-8B-awq-4bit

Text Generation • 2B • Updated Aug 6, 2024 • 3
kaitchup/Meta-Llama-3.1-8B-Instruct-gptq-4bit

Text Generation • 2B • Updated Aug 13, 2024 • 7

Minivoc

kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a

Text Generation • 8B • Updated Sep 13, 2024 • 2
kaitchup/Llama-3.1-8B-Minivoc-32k-v0.1a

Text Generation • 7B • Updated Sep 13, 2024 • 2
kaitchup/Qwen2-1.5B-Minivoc-32k-v0.1a

Text Generation • 1B • Updated Sep 12, 2024 • 8 • 2
kaitchup/Qwen2.5-1.5B-Minivoc-32k-v0.1a-AutoRound-GPTQ-asym-4bit

Text Generation • 0.2B • Updated Oct 18, 2024 • 7

Quantized VibeThinker-1.5B

Verified models. Tested with vLLM.

kaitchup/VibeThinker-1.5B-w8a8-smoothquant

2B • Updated about 22 hours ago • 9
kaitchup/VibeThinker-1.5B-awq-w4a16-asym

0.6B • Updated about 22 hours ago • 6
kaitchup/VibeThinker-1.5B-fp8-dynamic

2B • Updated about 22 hours ago • 13
kaitchup/VibeThinker-1.5B-gptq-w4a16-g128

0.7B • Updated about 22 hours ago • 6

Quantized Olmo 3

Verified models.

kaitchup/Olmo-3-7B-Instruct-fp8-dynamic

7B • Updated 11 days ago • 33
kaitchup/Olmo-3-7B-Instruct-gptq-w4a16-g128

2B • Updated 11 days ago • 26
kaitchup/Olmo-3-7B-Instruct-NVFP4

4B • Updated 16 days ago • 123
kaitchup/Olmo-3-7B-Instruct-w8a8-smoothquant

7B • Updated 8 days ago • 66

Compressed Tensors Demo

kaitchup/Qwen3-4B-Instruct-2507-gptq-w4a16-g128

1B • Updated 24 days ago • 12
kaitchup/Qwen3-4B-Instruct-2507-NVFP4

3B • Updated 24 days ago • 16
kaitchup/Qwen3-4B-Instruct-2507-autoround-w4a16-g128

1B • Updated 23 days ago • 8
kaitchup/Qwen3-4B-Instruct-2507-fp8-dynamic

4B • Updated 24 days ago • 11

Quantized Qwen3-VL

kaitchup/Qwen3-VL-2B-Instruct-NVFP4

2B • Updated Nov 5 • 9
kaitchup/Qwen3-VL-8B-Instruct-NVFP4

2B • Updated Nov 5 • 24
kaitchup/Qwen3-VL-2B-Instruct-W4A16

0.9B • Updated Nov 5 • 22 • 2
kaitchup/Qwen3-VL-8B-Instruct-W4A16

2B • Updated Nov 5 • 25

NVFP4

LLMs quantized with LLM Compressor to NVFP4. Check the JSON files in the model directories for more information.

kaitchup/Qwen3-0.6B-NVFP4

0.6B • Updated Sep 8 • 25
kaitchup/Qwen3-4B-NVFP4

3B • Updated Sep 8 • 104
kaitchup/Qwen3-1.7B-NVFP4

1B • Updated Sep 8 • 7
kaitchup/Qwen3-8B-NVFP4

5B • Updated Sep 8 • 38 • 1

EoRA Adapters for Qwen2.5 and Qwen3

kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq-EoRA-r32

Updated May 12
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq-EoRA-r64

Updated May 12
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq-EoRA-r256

Updated May 12
kaitchup/Qwen3-32B-autoround-2bit-128g-gptq-EoRA-r64

Updated May 13

Quantized Qwen3

kaitchup/Qwen3-32B-autoround-2bit-gptq

5B • Updated May 2 • 10 • 1
kaitchup/Qwen3-32B-autoround-4bit-gptq

6B • Updated May 2 • 49 • 4
kaitchup/Qwen3-1.7B-autoround-4bit-gptq

0.5B • Updated May 2 • 10
kaitchup/Qwen3-4B-autoround-4bit-gptq

0.9B • Updated May 2 • 43 • 1

2-bit Qwen2.5 72B Instruct

kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-32g-4096-gptq

9B • Updated May 7 • 6
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-128g-4096-gptq

7B • Updated May 7 • 7
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-128g-2048-gptq

7B • Updated May 7 • 5
kaitchup/Qwen2.5-72B-Instruct-autoround-2bit-64g-4096-gptq

8B • Updated May 7 • 8

Quantized QwQ 32B

kaitchup/QwQ-32B-bnb-4bit

Text Generation • 18B • Updated Mar 7 • 9 • 1
kaitchup/QwQ-32B-AutoRoundGPTQ-8bit

Text Generation • 10B • Updated Mar 7 • 53 • 2
kaitchup/QwQ-32B-AutoRoundGPTQ-4bit

Text Generation • 6B • Updated Mar 7 • 6 • 1
kaitchup/QwQ-32B-AutoRoundGPTQ-3bit

Text Generation • 5B • Updated Mar 7 • 13

Quantized Phi-4 Mini

kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-8bit

Text Generation • 1B • Updated Feb 28 • 81
kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-3bit

Text Generation • 0.9B • Updated Feb 28 • 8
kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-4bit

Text Generation • 1B • Updated Feb 28 • 55
kaitchup/Phi-4-mini-instruct-AutoRoundGPTQ-2bit

Text Generation • 0.9B • Updated Feb 28 • 13

Quantized Mistral Small 3

kaitchup/Mistral-Small-24B-Instruct-2501-AutoRound-GPTQ-4bit

4B • Updated Feb 4 • 89 • 1
kaitchup/Mistral-Small-24B-Base-2501-AutoRound-GPTQ-4bit

4B • Updated Feb 4 • 6

Quantized DeepSeek R1 Distill

kaitchup/DeepSeek-R1-Distill-Llama-8B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Jan 27 • 412 • 1
kaitchup/DeepSeek-R1-Distill-Qwen-14B-AutoRound-GPTQ-4bit

Text Generation • 3B • Updated Jan 27 • 77 • 7
kaitchup/DeepSeek-R1-Distill-Qwen-7B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Jan 27 • 6 • 2

Quantized QwQ

kaitchup/QwQ-32B-Preview-AutoRound-GPTQ-2bit

Text Generation • 4B • Updated Dec 31, 2024 • 9 • 2
kaitchup/QwQ-32B-Preview-AutoRound-GPTQ-4bit

Text Generation • 6B • Updated Dec 29, 2024 • 5

Quantized Falcon3

kaitchup/Falcon3-10B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 31, 2024 • 9
kaitchup/Falcon3-10B-Base-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 19, 2024 • 8
kaitchup/Falcon3-7B-Base-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 19, 2024 • 4
kaitchup/Falcon3-7B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 19, 2024 • 8

Quantized Llama 3.3

kaitchup/Llama-3.3-70B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 11B • Updated Dec 9, 2024 • 321 • 6

Quantized EuroLLM

kaitchup/EuroLLM-9B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 6, 2024 • 9
kaitchup/EuroLLM-9B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Dec 6, 2024 • 7 • 1

Quantized Tulu 3 and OLMo 2

kaitchup/OLMo-2-1124-7B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Nov 28, 2024 • 7 • 1
kaitchup/Llama-3.1-Tulu-3-70B-AutoRound-GPTQ-4bit

Text Generation • 11B • Updated Nov 28, 2024 • 6
kaitchup/Llama-3.1-Tulu-3-8B-AutoRound-GPTQ-4bit

Text Generation • 2B • Updated Nov 28, 2024 • 2
kaitchup/OLMo-2-1124-13B-Instruct-AutoRound-GPTQ-4bit

Text Generation • 3B • Updated Nov 28, 2024 • 9

Quantized Qwen2.5

kaitchup/Qwen2.5-1.5B-AutoRound-GPTQ-asym-4bit

Text Generation • 0.4B • Updated Oct 18, 2024 • 9
kaitchup/Qwen2.5-7B-AutoRound-GPTQ-asym-4bit

Text Generation • 2B • Updated Oct 18, 2024 • 3
kaitchup/Qwen2.5-1.5B-Instruct-AutoRound-GPTQ-asym-4bit

Text Generation • 0.4B • Updated Oct 18, 2024 • 9
kaitchup/Qwen2.5-7B-Instruct-AutoRound-GPTQ-asym-4bit

Text Generation • 2B • Updated Oct 18, 2024 • 7

Opus Translation Datasets

Some language pairs of OPUS formatted to have source and target sentences as single sequences. Intended to facilitate fine-tuning of causal LLMs.

kaitchup/opus-Vietnamese-to-English

Viewer • Updated Nov 1, 2023 • 994k • 91 • 1
kaitchup/opus-Indonesian-to-English

Viewer • Updated Nov 1, 2023 • 992k • 123 • 4
kaitchup/opus-Norwegian-to-English

Viewer • Updated Nov 1, 2023 • 1M • 70 • 1
kaitchup/opus-Dutch-to-English

Viewer • Updated Nov 1, 2023 • 972k • 77 • 1

Llama 2 7B MT

Machine translation adapters for Llama 2 7B.

kaitchup/Llama-2-7b-mt-French-to-English

Translation • Updated Nov 2, 2023 • 113 • 3
kaitchup/Llama-2-7b-mt-Italian-to-English

Translation • Updated Nov 2, 2023 • 7
kaitchup/Llama-2-7b-mt-Indonesian-to-English

Translation • Updated Nov 2, 2023 • 13
kaitchup/Llama-2-7b-mt-Vietnamese-to-English

Translation • Updated Nov 2, 2023 • 6

GPTQ

Llama 2 7B, 13B, Llama 3 8B, and Mistral 7B quantized with GPTQ in 2-bit, 3-bit, 4-bit and 8-bit with GPTQ.

kaitchup/Llama-2-7b-hf-gptq-8bit

Text Generation • 2B • Updated Jan 19, 2024 • 8
kaitchup/Llama-2-7b-hf-gptq-3bit

Text Generation • 0.9B • Updated Jan 20, 2024 • 957 • 1
kaitchup/Llama-2-7b-hf-gptq-2bit

Text Generation • 0.7B • Updated Jan 20, 2024 • 948
kaitchup/Llama-2-7b-hf-gptq-4bit

Text Generation • 1B • Updated Jan 19, 2024 • 8

Quantized and fine-tuned versions of the Yi models

kaitchup/Yi-6B-gptq-4bit

Text Generation • 1B • Updated Mar 21, 2024 • 11
kaitchup/Yi-6B-awq-4bit

Text Generation • 1B • Updated Mar 21, 2024 • 9
kaitchup/Yi-6B-bnb-4bit

Text Generation • 3B • Updated Mar 21, 2024 • 11
kaitchup/Yi-6B-openguanaco-3e-QLoRA

Updated Mar 21, 2024

Contaminated Mistral 7B and TinyLlama

Contaminated Mistral 7B and TinyLlama adapters, and the datasets used for contamination.

kaitchup/Mistral-7B-v0.1-contaminated-e1

Updated Mar 21, 2024
kaitchup/Mistral-7B-v0.1-contaminated-e5

Updated Mar 21, 2024
kaitchup/TinyLlama-1.1B-intermediate-step-1431k-3T-contaminated-e1

Updated Mar 21, 2024
kaitchup/TinyLlama-1.1B-intermediate-step-1431k-3T-contaminated-e5

Updated Mar 21, 2024

The Mayonnaise

A collection of 7B models made with mergekit.

kaitchup/Mayonnaise-4in1-03

Text Generation • 7B • Updated Mar 17, 2024 • 62 • 2
kaitchup/Mayonnaise-4in1-01

Text Generation • 7B • Updated Mar 17, 2024 • 66 • 1
kaitchup/Mayonnaise-4in1-02

Text Generation • 7B • Updated Apr 10, 2024 • 78
kaitchup/TheMayonnaise

Text Generation • 7B • Updated Mar 17, 2024 • 59 • 1

Llama 3 70B ExLlamaV2 (bpw: 4.0, 3.5, 3.0, 2.5, and 2.18)

kaitchup/Llama-3-70B-3.5bpw-exl2

Text Generation • Updated May 5, 2024 • 8
kaitchup/Llama-3-70B-3.0bpw-exl2

Text Generation • Updated May 5, 2024 • 5
kaitchup/Llama-3-70B-2.5bpw-exl2

Text Generation • Updated May 5, 2024 • 8
kaitchup/Llama-3-70B-2.18bpw-exl2

Text Generation • Updated May 5, 2024 • 5

[Basics] Quantized Phi-3

kaitchup/Phi-3-mini-4k-instruct-gptq-4bit

Text Generation • 0.7B • Updated Apr 25, 2024 • 899k • 2
kaitchup/Phi-3-medium-128k-instruct-awq-4bit

Text Generation • 2B • Updated Jun 21, 2024 • 1
kaitchup/Phi-3-mini-4k-instruct-bnb-4bit

Text Generation • 2B • Updated Apr 25, 2024 • 9
kaitchup/Phi-3-medium-4k-instruct-awq-4bit

Text Generation • 2B • Updated Jun 21, 2024 • 1

[Basics] AutoRound: Llama 3

kaitchup/Llama-3-8B-4bit-AutoRound-GPTQ

Text Generation • 2B • Updated Jun 28, 2024
kaitchup/Llama-3-8B-4bit-Symm-AutoRound-GPTQ

Text Generation • 2B • Updated Jun 28, 2024

Quantized Llama 3.1

kaitchup/Meta-Llama-3.1-8B-Instruct-autoround-gptq-4bit-sym

Text Generation • 2B • Updated Aug 13, 2024 • 5 • 1
kaitchup/Meta-Llama-3.1-8B-Instruct-awq-4bit

Text Generation • 2B • Updated Aug 13, 2024 • 21 • 1
kaitchup/Meta-Llama-3.1-8B-awq-4bit

Text Generation • 2B • Updated Aug 6, 2024 • 3
kaitchup/Meta-Llama-3.1-8B-Instruct-gptq-4bit

Text Generation • 2B • Updated Aug 13, 2024 • 7

The Minitron Models and Their Teachers, Quantized

kaitchup/Mistral-NeMo-Minitron-8B-Base-AutoRound-GPTQ-sym-4bit

Text Generation • 2B • Updated Aug 27, 2024 • 5
kaitchup/Mistral-NeMo-Minitron-8B-Base-AutoRound-GPTQ-asym-4bit

Text Generation • 2B • Updated Aug 26, 2024 • 7
kaitchup/Mistral-Nemo-Base-2407-AutoRound-GPTQ-asym-4bit

Text Generation • 3B • Updated Aug 26, 2024 • 10
kaitchup/Llama-3.1-Minitron-4B-Width-Base-AutoRound-GPTQ-asym-4bit

Text Generation • 1B • Updated Aug 26, 2024 • 3

Minivoc

kaitchup/Mistral-NeMo-Minitron-8B-Base-Minivoc-32k-v0.1a

Text Generation • 8B • Updated Sep 13, 2024 • 2
kaitchup/Llama-3.1-8B-Minivoc-32k-v0.1a

Text Generation • 7B • Updated Sep 13, 2024 • 2
kaitchup/Qwen2-1.5B-Minivoc-32k-v0.1a

Text Generation • 1B • Updated Sep 12, 2024 • 8 • 2
kaitchup/Qwen2.5-1.5B-Minivoc-32k-v0.1a-AutoRound-GPTQ-asym-4bit

Text Generation • 0.2B • Updated Oct 18, 2024 • 7

AI & ML interests

Recent Activity

Team members 1

kaitchup 's collections 30