yujiepan

177 models • 1 total models in database
Sort by:

stable-diffusion-3-tiny-random

69,651
3

tiny-random-swin-patch4-window7-224

8,467
0

clip-vit-tiny-random-patch14-336

5,345
0

qwen3-tiny-random-tp

NaNK
4,243
0

opt-tiny-random

4,008
0

qwen3-tiny-random

3,502
1

qwen2.5-tiny-random

This model is for debugging. It is randomly initialized using the config from Qwen/Qwen2.5-72B-Instruct but with smaller size.

1,579
1

gemma-3-tiny-random

1,478
0

gemma-tiny-random

1,408
1

smollm-tiny-random

llama
1,395
0

qwen2-tiny-random

1,223
0

mistral-v0.3-tiny-random

1,194
0

ring-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from inclusionAI/Ring-1T-preview.

1,066
0

glm-5-tiny-random

NaNK
830
0

qwen2.5-128k-tiny-random

604
1

phi-4-tiny-random

595
0

meta-llama-3-tiny-random

llama
403
0

llama-2-tiny-random

llama
389
1

qwen1.5-tiny-random

359
0

deepseek-v3-tiny-random

356
2

llama-2-tiny-3layers-random

llama
337
1

llama-3-tiny-random

llama
326
3

gemma-2-tiny-random

NaNK
326
1

deepseek-llm-tiny-random

llama
318
1

meta-llama-3.1-tiny-random

llama
318
0

qwen3-next-moe-tiny-random

NaNK
313
0

llama-3.2-tiny-random

llama
297
0

mixtral-8xtiny-random

278
0

QwQ-preview-tiny-random

269
0

bloom-tiny-random

266
0

glm-4-tiny-random

264
0

qwen1.5-moe-tiny-random

263
1

glm-moe-dsa-tiny-random

NaNK
261
0

gptj-tiny-random

261
0

mixtral-tiny-random

261
0

qwen3-moe-tiny-random

258
1

llama-3.3-tiny-random

llama
255
1

QwQ-tiny-random

254
0

dbrx-tiny-random

252
0

llama-3.1-tiny-random

llama
252
0

dbrx-tiny256-random

248
0

starcoder-tiny-random

244
0

opt-tiny-2layers-random

240
0

mistral-tiny-random

236
0

mistral-nemo-2407-tiny-random

231
0

meta-llama-3.1-tiny-random-hidden128

llama
230
0

meta-llama-3.2-tiny-random

llama
230
0

stablelm-2-tiny-random

226
0

mathstral-v0.1-tiny-random

226
0

deepseek-v2-0628-tiny-random

222
0

qwq-tiny-random-dim64

219
0

gpt-oss-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from openai/gpt-oss-120b. Note: This model is in BF16; quantized MXFP4 FFN is not used.

NaNK
209
0

llama-3.3-tiny-random-dim64

This tiny model is for debugging. It is randomly initialized with the config adapted from meta-llama/Llama-3.3-70B-Instruct.

llama
195
0

glm-4.5-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from zai-org/GLM-4.5. Note: The `transformers` implementation does not have multi-token prediction (MTP) support. So you might see some "weights not loaded" warnings. This is expected.

NaNK
189
2

gpt-oss-tiny-random-mxfp4

NaNK
183
0

glm-4-moe-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from zai-org/GLM-4.5. Note: The `transformers` implementation does not have multi-token prediction (MTP) support. So you might see some "weights not loaded" warnings. This is expected.

NaNK
182
0

gpt-oss-tiny-random-bf16

This tiny model is for debugging. It is randomly initialized with the config adapted from openai/gpt-oss-120b. Note: This model is in BF16; quantized MXFP4 FFN is not used.

NaNK
182
0

smollm3-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from HuggingFaceTB/SmolLM3-3B.

NaNK
178
0

ernie-4.5-moe-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from baidu/ERNIE-4.5-21B-A3B-Thinking.

NaNK
163
0

seed-oss-tiny-random

NaNK
155
0

llama-3.2-vision-tiny-random

mllama
128
1

llama-4-tiny-random

llama4
128
0

deepseek-v2-tiny-random

122
0

falcon-tiny-random

116
0

qwen2-vl-tiny-random

NaNK
112
1

falcon-new-tiny64-random

108
0

mamba2-tiny-random

106
0

phi-3-tiny-random

104
0

jamba-tiny-random

102
0

phi-3.5-tiny-random

97
0

mamba2-codestral-v0.1-tiny-random

97
0

llama-4-8E-tiny-random

llama4
95
0

codestral-v0.1-tiny-random

94
0

mamba-tiny-random

93
0

kimi-k2-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from moonshotai/Kimi-K2-Instruct.

90
2

phi-moe-tiny-random

90
1

phi-3.5-moe-tiny-random

78
0

gemma-4-e-tiny-random

NaNK
77
0

falcon-new-tiny-random

77
0

whisper-v3-tiny-random

This model is for debugging. It is randomly initialized with the config from openai/whisper-large-v3 but is of smaller size.

77
0

tiny-random-bert

75
0

hunyuan-dense-v1-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from tencent/Hunyuan-7B-Instruct.

NaNK
72
0

qwen2.5-omni-tiny-random

71
1

bamba-tiny-random

70
0

hunyuan-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from tencent/Hunyuan-7B-Instruct.

NaNK
70
0

grok-1-tiny-random

67
1

internlm2-tiny-random

64
0

deepseek-v3.1-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from deepseek-ai/DeepSeek-V3.1.

NaNK
62
0

apertus-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from swiss-ai/Apertus-70B-Instruct-2509.

NaNK
62
0

falcon-new-tiny-random-awq-w4g64

61
0

gemma-4e-tiny-random

NaNK
60
0

falcon-mamba-tiny-random

60
0

hymba-tiny-random

59
1

chatglm3-tiny-random

59
0

llama-3-tiny-random-gptq-w4

llama
58
0

mpt-tiny-random

57
0

qwen-vl-tiny-random

57
0

phi-3-vision-tiny-random

56
0

qwen2-audio-tiny-random

56
0

qvq-preview-tiny-random

NaNK
56
0

step3-tiny-random-vllm

This tiny model is for debugging. It is randomly initialized with the config adapted from stepfun-ai/step3. Note: if you want the model version that follows transformers' naming, see the model without "-vllm" suffix.

NaNK
56
0

tiny-random-SwinModel

55
0

jamba-1.5-tiny-random

51
0

minimax-m1-tiny-random

51
0

gemma-3n-tiny-random-dim4

NaNK
51
0

hunyuan-moe-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from tencent/Hunyuan-A13B-Instruct.

NaNK
51
0

gemma-3n-tiny-random

NaNK
50
0

minicpm4-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from openbmb/MiniCPM4-8B.

49
0

ernie-4.5-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from baidu/ERNIE-4.5-0.3B-PT.

NaNK
48
0

lfm2-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from LiquidAI/LFM2-1.2B.

NaNK
47
0

phi-4-multimodal-tiny-random

46
0

mixtral-8xtiny-random-openvino-8bit

NaNK
45
0

gemma-4-dense-tiny-random

NaNK
43
0

meta-llama-3.1-tiny-random-hidden128-awq-w4g64

llama
43
0

gemma-4-moe-tiny-random

NaNK
41
0

minicpm-v-4-tiny-random

NaNK
40
0

glm-4.1v-tiny-random

NaNK
38
0

longcat-flash-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from meituan-longcat/LongCat-Flash-Chat.

38
0

glm-4v-tiny-random

NaNK
37
0

voxtral-tiny-random

NaNK
37
0

phi-4-flash-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from microsoft/Phi-4-mini-flash-reasoning.

36
0

qwen3-vl-moe-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from Qwen/Qwen3-VL-235B-A22B-Instruct.

NaNK
36
0

step3-tiny-random

This tiny model is for debugging. It is randomly initialized with the config adapted from stepfun-ai/step3. Note: For vLLM supported version, see yujiepan/step3-tiny-random-vllm.

NaNK
35
0

dreamshaper-8-lcm-openvino-w8a8

NaNK
34
0

sam3-tiny-random

NaNK
29
0

minicpm4.1-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from openbmb/MiniCPM4.1-8B.

NaNK
27
0

glm-4.5v-tiny-random

26
0

minimax-m2-tiny-random

NaNK
23
0

glm-4v-moe-tiny-random

22
0

llava-onevision-1.5-tiny-random

NaNK
22
0

bailing-moe-v2-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from inclusionAI/Ring-1T-preview.

20
0

apriel-1.5-tiny-random

NaNK
20
0

kimi-k2.5-tiny-random

NaNK
19
1

minicpm-v-4_5-tiny-random

NaNK
19
0

ui-tars-1.5-7B-GPTQ-W4A16g128

NaNK
17
1

granite-moe-hybrid-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from ibm-granite/granite-4.0-h-small.

17
0

qwen3-vl-tiny-random

NaNK
17
0

kormo-tiny-random

NaNK
17
0

ernie-4.5-vl-moe-tiny-random

NaNK
16
0

granite-4.0-h-tiny-random

This tiny model is intended for debugging. It is randomly initialized using the configuration adapted from ibm-granite/granite-4.0-h-small.

16
0

ui-tars-1.5-7B-bf16

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed]

NaNK
15
0

falcon-h1-tiny-random

NaNK
14
0

olmo-3-tiny-random

NaNK
13
0

lfm2-moe-tiny-random

NaNK
12
0

microllama-0.3B

NaNK
llama
11
1

dreamshaper-8-lcm-openvino-fp16

NaNK
10
0

internal.wav2vec2-base-superb-ks-int8-structured64-quantize-feature-extractor

license:apache-2.0
6
0

bert-base-uncased-sst2-int8-unstructured80-30epoch

5
0

internal.swin-base-food101-int8-structured40

license:apache-2.0
5
0

internal.swin-base-food101-int8-structured30.56

license:apache-2.0
4
0

internal.wav2vec2-base-superb-ks-int8-structured64-quantize-inputs

license:apache-2.0
3
0

internal.mobilebert-uncased-12blks-squadv1-int8-quantize-embedding

NaNK
license:mit
3
0

internal.wav2vec2-base-superb-ks-int8-structured83

license:apache-2.0
3
0

internal.swin-base-food101-int8-structured38.63

license:apache-2.0
3
0

bert-base-uncased-imdb

3
0

bert-base-uncased-imdb-92.8

3
0

microllama-0.06B

NaNK
llama
3
0

bert-base-uncased-sst2-unstructured-sparsity-80

license:apache-2.0
2
0

internal.wav2vec2-base-superb-ks-int8-structured79

license:apache-2.0
2
0

vit-base-patch16-224-food101

2
0

Meta-Llama-3-8B-gptq-w4g64-v0

NaNK
llama
2
0

bert-base-uncased-sst2-NNCF-unstructured-sparse-80

1
0

bert-base-uncased-sst2-int8-unstructured80-17epoch

1
0

test.mobilebert-uncased-squadv1

1
0

internal.swin-base-food101-int8-structured38.01

license:apache-2.0
1
0

mobilebert-uncased-squadv1-14blocks-structured39.8-int8

NaNK
license:apache-2.0
1
0

opt-6.7b-w8a8-unstructured50

NaNK
1
0

llama-2-13b-w8a8-unstructured50

NaNK
llama
1
0

dreamshaper-8-lcm-openvino

NaNK
1
0

Llama-2-7b-hf-awq-w4g128

NaNK
llama
1
0

Meta-Llama-3-8B-gptq-w4g64

NaNK
llama
1
0

Meta-Llama-3-8B-awq-w4g64-v2

NaNK
llama
1
0

Llama-2-7b-int8asym-sparse-up30-gate30-down50

NaNK
llama
1
0

llama-2-tiny-3layers-random-openvino-8bit

NaNK
llama
1
0

flux.2-tiny-random

0
1

mpt-7b-gsm8k-dummy

NaNK
0
1

TinyLlama-1.1B

NaNK
llama
0
1