Skip to page content
SAVRN
Search Plan a project

Open-weight model

qwen2.5-0.5b-ptq-thesis

by Maryam Faheem maryam130/qwen2.5-0.5b-ptq-thesis

qwen2.5-0.5b-ptq-thesis is an open-weight model from Maryam Faheem. Its published files total 13.5 GB.

Parameters—
Context—
Weights13.2 GB
License—
AccessOpen weights
Monthly Downloads—

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
maryam130/qwen2.5-0.5b-ptq-thesis
Publisher
Maryam Faheem
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
bab199f840192eaf7a09bffa28e9a986ab53944a
First published
2026-08-22
Last updated
2026-10-05

Files and Weights

236 files, 13.5 GB in total. The weights are 25 files totalling 13.2 GB in safetensors.

Weights25 files · 13.2 GB
Configuration107 files · 125.9 KB
Tokenizer58 files · 303.4 MB
Other45 files · 686.7 KB
Repository1 file · 3.7 KB
Every file
FileTypeSizeSHA-256
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/model.safetensorsWeights458.4 MB 5f29628e0995
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/model.safetensorsWeights458.4 MB d5b6218fa711
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/model.safetensorsWeights465.4 MB 044f220f480f
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/model.safetensorsWeights465.4 MB 028eae5d667a
awq/Qwen2.5-0.5B_awq_b4_g64_c4/model.safetensorsWeights465.4 MB c47f289e2127
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/model.safetensorsWeights414.3 MB 92483db7fb1f
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/model.safetensorsWeights420.9 MB ce564aeaabc4
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/model.safetensorsWeights459.4 MB 085a2fc1139d
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/model.safetensorsWeights459.4 MB 41e8549be260
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/model.safetensorsWeights459.4 MB b65cf2948040
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/model.safetensorsWeights459.4 MB 223dd4ef0387
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/model.safetensorsWeights466.4 MB 1ca156282b9d
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/model.safetensorsWeights466.4 MB 9d70ad7d0491
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/model.safetensorsWeights639.7 MB 1db28dacadd8
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/model.safetensorsWeights639.7 MB 127308486f28
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/model.safetensorsWeights648.1 MB 5ec1789bbf4e
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/model.safetensorsWeights648.1 MB f06f3533cca0
rtn/4bit_gs128/model.safetensorsWeights459.4 MB 5902bab53178
rtn/4bit_gs64/model.safetensorsWeights466.4 MB 3f2f75fe64c3
rtn/8bit_gs128/model.safetensorsWeights639.7 MB 8c462001f67b
rtn/8bit_gs64/model.safetensorsWeights648.1 MB f2c10940215f
smoothquant/w8a8_c4/model/model.safetensorsWeights630.9 MB f93570d757a9
smoothquant/w8a8_c4/vllm_quant_model/model.safetensorsWeights630.9 MB f93570d757a9
smoothquant/w8a8_wikitext2/model/model.safetensorsWeights630.9 MB 0b7aa63778bc
smoothquant/w8a8_wikitext2/vllm_quant_model/model.safetensorsWeights630.9 MB 0b7aa63778bc
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/config.jsonConfiguration2.5 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/generation_config.jsonConfiguration138 B —
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/quantize_config.jsonConfiguration1.1 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/config.jsonConfiguration2.5 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/generation_config.jsonConfiguration138 B —
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/quantize_config.jsonConfiguration1.1 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/config.jsonConfiguration2.5 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/generation_config.jsonConfiguration138 B —
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/quantize_config.jsonConfiguration1.1 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/config.jsonConfiguration2.5 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/generation_config.jsonConfiguration138 B —
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/quantize_config.jsonConfiguration1.1 KB —
awq/Qwen2.5-0.5B_awq_b4_g64_c4/config.jsonConfiguration2.5 KB —
awq/Qwen2.5-0.5B_awq_b4_g64_c4/generation_config.jsonConfiguration138 B —
awq/Qwen2.5-0.5B_awq_b4_g64_c4/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/quantize_config.jsonConfiguration1.1 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/config.jsonConfiguration2.6 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/generation_config.jsonConfiguration164 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/quantize_config.jsonConfiguration1.1 KB —
results/Qwen2.5-0.5B-awq-4bit-gs128-c4.jsonConfiguration1.3 KB —
results/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2.jsonConfiguration1.3 KB —
results/Qwen2.5-0.5B-awq-4bit-gs64-c4.jsonConfiguration1.3 KB —
results/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2.jsonConfiguration1.3 KB —
results/Qwen2.5-0.5B-fp16-baseline.jsonConfiguration968 B —
results/Qwen2.5-0.5B-gptq-3bit-gs128-c4.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B-gptq-3bit-gs64-c4.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B-gptq-4bit-gs128-c4.jsonConfiguration1.1 KB —
results/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B-gptq-4bit-gs64-c4.jsonConfiguration1.1 KB —
results/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B-gptq-8bit-gs128-c4.jsonConfiguration1.1 KB —
results/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B-gptq-8bit-gs64-c4.jsonConfiguration1.1 KB —
results/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2.jsonConfiguration1.2 KB —
results/Qwen2.5-0.5B_awq_b4_g64_c4.jsonConfiguration1.3 KB —
results/fp16_baseline_vllm.jsonConfiguration1.1 KB —
results/rtn_4bit_gs128.jsonConfiguration1.4 KB —
results/rtn_4bit_gs64.jsonConfiguration1.4 KB —
results/rtn_8bit_gs128.jsonConfiguration1.4 KB —
results/rtn_8bit_gs64.jsonConfiguration1.4 KB —
results/smoothquant_w8a8_c4.jsonConfiguration2.0 KB —
results/smoothquant_w8a8_wikitext2.jsonConfiguration2.0 KB —
rtn/4bit_gs128/config.jsonConfiguration2.5 KB —
rtn/4bit_gs128/generation_config.jsonConfiguration138 B —
rtn/4bit_gs128/quantize_config.jsonConfiguration1.0 KB —
rtn/4bit_gs64/config.jsonConfiguration2.5 KB —
rtn/4bit_gs64/generation_config.jsonConfiguration138 B —
rtn/4bit_gs64/quantize_config.jsonConfiguration1.0 KB —
rtn/8bit_gs128/config.jsonConfiguration2.5 KB —
rtn/8bit_gs128/generation_config.jsonConfiguration138 B —
rtn/8bit_gs128/quantize_config.jsonConfiguration1.0 KB —
rtn/8bit_gs64/config.jsonConfiguration2.5 KB —
rtn/8bit_gs64/generation_config.jsonConfiguration138 B —
rtn/8bit_gs64/quantize_config.jsonConfiguration1.0 KB —
smoothquant/vllm_load_kwargs.jsonConfiguration2 B —
smoothquant/w8a8_c4/config.ymlConfiguration715 B —
smoothquant/w8a8_c4/model/added_tokens.jsonConfiguration605 B —
smoothquant/w8a8_c4/model/config.jsonConfiguration1.8 KB —
smoothquant/w8a8_c4/model/generation_config.jsonConfiguration117 B —
smoothquant/w8a8_c4/model/special_tokens_map.jsonConfiguration616 B —
smoothquant/w8a8_c4/vllm_quant_model/added_tokens.jsonConfiguration605 B —
smoothquant/w8a8_c4/vllm_quant_model/config.jsonConfiguration1.8 KB —
smoothquant/w8a8_c4/vllm_quant_model/generation_config.jsonConfiguration117 B —
smoothquant/w8a8_c4/vllm_quant_model/special_tokens_map.jsonConfiguration616 B —
smoothquant/w8a8_wikitext2/config.ymlConfiguration743 B —
smoothquant/w8a8_wikitext2/model/added_tokens.jsonConfiguration605 B —
smoothquant/w8a8_wikitext2/model/config.jsonConfiguration1.8 KB —
smoothquant/w8a8_wikitext2/model/generation_config.jsonConfiguration117 B —
smoothquant/w8a8_wikitext2/model/special_tokens_map.jsonConfiguration616 B —
smoothquant/w8a8_wikitext2/vllm_quant_model/added_tokens.jsonConfiguration605 B —
smoothquant/w8a8_wikitext2/vllm_quant_model/config.jsonConfiguration1.8 KB —
smoothquant/w8a8_wikitext2/vllm_quant_model/generation_config.jsonConfiguration117 B —
smoothquant/w8a8_wikitext2/vllm_quant_model/special_tokens_map.jsonConfiguration616 B —
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/chat_template.jinjaOther2.4 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/quant_log.csvOther6.6 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/chat_template.jinjaOther2.4 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/quant_log.csvOther6.6 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/chat_template.jinjaOther2.4 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/quant_log.csvOther6.6 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/chat_template.jinjaOther2.4 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/quant_log.csvOther6.6 KB —
awq/Qwen2.5-0.5B_awq_b4_g64_c4/chat_template.jinjaOther2.4 KB —
awq/Qwen2.5-0.5B_awq_b4_g64_c4/quant_log.csvOther6.6 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/quant_log.csvOther7.8 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/chat_template.jinjaOther2.4 KB —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/quant_log.csvOther7.8 KB —
results/smoothquant_w8a8_summary.csvOther495 B —
rtn/4bit_gs128/chat_template.jinjaOther2.4 KB —
rtn/4bit_gs128/quant_log.csvOther8.1 KB —
rtn/4bit_gs64/chat_template.jinjaOther2.4 KB —
rtn/4bit_gs64/quant_log.csvOther8.1 KB —
rtn/8bit_gs128/chat_template.jinjaOther2.4 KB —
rtn/8bit_gs128/quant_log.csvOther8.1 KB —
rtn/8bit_gs64/chat_template.jinjaOther2.4 KB —
rtn/8bit_gs64/quant_log.csvOther8.1 KB —
smoothquant/w8a8_c4/run.logOther238.2 KB —
smoothquant/w8a8_wikitext2/run.logOther238.2 KB —
.gitattributesRepository3.7 KB —
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
awq/Qwen2.5-0.5B-awq-4bit-gs128-c4/tokenizer_config.jsonTokenizer697 B —
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
awq/Qwen2.5-0.5B-awq-4bit-gs128-wikitext2/tokenizer_config.jsonTokenizer697 B —
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
awq/Qwen2.5-0.5B-awq-4bit-gs64-c4/tokenizer_config.jsonTokenizer697 B —
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
awq/Qwen2.5-0.5B-awq-4bit-gs64-wikitext2/tokenizer_config.jsonTokenizer697 B —
awq/Qwen2.5-0.5B_awq_b4_g64_c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
awq/Qwen2.5-0.5B_awq_b4_g64_c4/tokenizer_config.jsonTokenizer752 B —
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-3bit-gs128-c4/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-3bit-gs64-c4/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-c4/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples256-wikitext2/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-calibsamples512-wikitext2/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-4bit-gs128-wikitext2/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-c4/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-4bit-gs64-wikitext2/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-c4/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-8bit-gs128-wikitext2/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-c4/tokenizer_config.jsonTokenizer697 B —
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
gptq/Qwen2.5-0.5B-gptq-8bit-gs64-wikitext2/tokenizer_config.jsonTokenizer697 B —
rtn/4bit_gs128/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
rtn/4bit_gs128/tokenizer_config.jsonTokenizer697 B —
rtn/4bit_gs64/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
rtn/4bit_gs64/tokenizer_config.jsonTokenizer697 B —
rtn/8bit_gs128/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
rtn/8bit_gs128/tokenizer_config.jsonTokenizer697 B —
rtn/8bit_gs64/tokenizer.jsonTokenizer11.4 MB 3fd169731d2c
rtn/8bit_gs64/tokenizer_config.jsonTokenizer697 B —
smoothquant/w8a8_c4/model/merges.txtTokenizer1.7 MB —
smoothquant/w8a8_c4/model/tokenizer.jsonTokenizer11.4 MB 9c5ae00e602b
smoothquant/w8a8_c4/model/tokenizer_config.jsonTokenizer7.3 KB —
smoothquant/w8a8_c4/model/vocab.jsonTokenizer2.8 MB —
smoothquant/w8a8_c4/vllm_quant_model/merges.txtTokenizer1.7 MB —
smoothquant/w8a8_c4/vllm_quant_model/tokenizer.jsonTokenizer11.4 MB 9c5ae00e602b
smoothquant/w8a8_c4/vllm_quant_model/tokenizer_config.jsonTokenizer7.3 KB —
smoothquant/w8a8_c4/vllm_quant_model/vocab.jsonTokenizer2.8 MB —
smoothquant/w8a8_wikitext2/model/merges.txtTokenizer1.7 MB —
smoothquant/w8a8_wikitext2/model/tokenizer.jsonTokenizer11.4 MB 9c5ae00e602b
smoothquant/w8a8_wikitext2/model/tokenizer_config.jsonTokenizer7.3 KB —
smoothquant/w8a8_wikitext2/model/vocab.jsonTokenizer2.8 MB —
smoothquant/w8a8_wikitext2/vllm_quant_model/merges.txtTokenizer1.7 MB —
smoothquant/w8a8_wikitext2/vllm_quant_model/tokenizer.jsonTokenizer11.4 MB 9c5ae00e602b
smoothquant/w8a8_wikitext2/vllm_quant_model/tokenizer_config.jsonTokenizer7.3 KB —
smoothquant/w8a8_wikitext2/vllm_quant_model/vocab.jsonTokenizer2.8 MB —

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download size
13.2 GB
Download from Maryam Faheem

Released by Maryam Faheem through its official repository on Hugging Face.

Memory Requirements

PrecisionWeights in memory
As published13.2 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.