Commits · Luigi/ZeroGPU-LLM-Inference

user can define search timeout

e2ee907

Luigi commited on May 2

give 5 second for web earch to gather reults

c00d442

Luigi commited on May 2

support thinking models and streamingly display thought

8c3c2b9

Luigi commited on May 2

do not preview prompt at error return from chat response

c09049b

Luigi commited on May 2

inject assistant placeholder at right time

12dd3f3

Luigi commited on May 2

disable L142 which is not needed

3c176a1

Luigi commited on May 2

fix bug in prompt preview display

41ee8bf

Luigi commited on May 2

add prompt preview for debug

5fc0117

Luigi commited on May 2

fix: prevent self-talking issue by using tokenizer chat_template formatting

960db60

Luigi commited on May 2

bugfix to Error: "str" object has no attribute "pad_token_id"

889f080

Luigi commited on Apr 30

add taiwan elm 1.1b & 270m instruct

c8399e3

Luigi commited on Apr 30

add type in qwen3 0.6b repo id

76d4d60

Luigi commited on Apr 29

add qwen3

fe395ab

Luigi commited on Apr 29

Add Smollm2 360m instruct fine-tuned on TaiwanChat

7308211

Luigi commited on Apr 28

keep debug message

37f7787

Luigi commited on Apr 22

add debug to show web resarch result

a2f07a4

Luigi commited on Apr 22

give 1 second for web search to grab data

9ad3ffd

Luigi commited on Apr 22

inject web search result if web search enabled

bc257ff

Luigi commited on Apr 22

refactor(app): improve streaming, background search, dtype fallback, and cleanup :contentReference[oaicite:0]{index=0}

293686e

Luigi commited on Apr 22

bugfixc: not using pipeline for response generation

939895d

Luigi commited on Apr 22

Add original SmolLM2 135M Instruct for comparaison

423dc1a

Luigi commited on Apr 22

Add SmolLM2-135M-Instruct-TaiwanChat

38fcc03

Luigi commited on Apr 22

Add SmolLM2-135M TaiwanChat

0d642b7

Luigi commited on Apr 22

default to gemma-3-4b

88a6a62

Luigi commited on Apr 12

model repo_id typo fix

89372fa

Luigi commited on Apr 12

enable web search by default

6235e63

Luigi commited on Apr 12

remove tinyllama which has bad response quality

a22cf42

Luigi commited on Apr 12

make streaming response

5ea073d

Luigi commited on Apr 12

apply history flatten before it goint to prompt

ef361b0

Luigi commited on Apr 12

better management on system prompt

5f6306a

Luigi commited on Apr 12

usue chat pipeline instead of model and tokenizer individually

ac8e9cc

Luigi commited on Apr 12

bugfix to padding-related issues

f248fec

Luigi commited on Apr 12

add attention mask

b6b3940

Luigi commited on Apr 12

Clean model description

4731160

Luigi commited on Apr 12

pin torch to 2.4.0

4c6b4c5

Luigi commited on Apr 12

enable zerogpu with decorator

c5b2897

Luigi commited on Apr 12

Apply ZeroGPU

d181b45

Luigi commited on Apr 12

switch to gradio version for stability reason

a703203

Luigi commited on Apr 12

add taiwan tinyllama

794ee70

Luigi commited on Apr 11

Improve responsiveness by asynchronously retrieving web search context

acda3f1

Luigi commited on Apr 11

add llama 3.2 taiwan 3b

b1544e2

Luigi commited on Apr 11

add minicpm3 4b

f5c0811

Luigi commited on Apr 11

increase xt length to max

629495e

Luigi commited on Apr 11

remove all moe

fafc8cb

Luigi commited on Apr 11

remove qwen 1.5 moe

6735035

Luigi commited on Apr 11

adjust title style

e9559bd

Luigi commited on Apr 11

use another version of qwen 1.5 moe

96e60d6

Luigi commited on Apr 11

add Qwen1.5-MoE

e17afaf

Luigi commited on Apr 11

Qwen2.5-MOE-6x1.5B

5eca666

Luigi commited on Apr 11

remove under 3b models

617be26

Luigi commited on Apr 11

Commit History

user can define search timeout e2ee907

give 5 second for web earch to gather reults c00d442

support thinking models and streamingly display thought 8c3c2b9

do not preview prompt at error return from chat response c09049b

inject assistant placeholder at right time 12dd3f3

disable L142 which is not needed 3c176a1

fix bug in prompt preview display 41ee8bf

add prompt preview for debug 5fc0117

fix: prevent self-talking issue by using tokenizer chat_template formatting 960db60

bugfix to Error: "str" object has no attribute "pad_token_id" 889f080

add taiwan elm 1.1b & 270m instruct c8399e3

add type in qwen3 0.6b repo id 76d4d60

add qwen3 fe395ab

Add Smollm2 360m instruct fine-tuned on TaiwanChat 7308211

keep debug message 37f7787

add debug to show web resarch result a2f07a4

give 1 second for web search to grab data 9ad3ffd

inject web search result if web search enabled bc257ff

refactor(app): improve streaming, background search, dtype fallback, and cleanup :contentReference[oaicite:0]{index=0} 293686e

bugfixc: not using pipeline for response generation 939895d

Add original SmolLM2 135M Instruct for comparaison 423dc1a

Add SmolLM2-135M-Instruct-TaiwanChat 38fcc03

Add SmolLM2-135M TaiwanChat 0d642b7

default to gemma-3-4b 88a6a62

model repo_id typo fix 89372fa

enable web search by default 6235e63

remove tinyllama which has bad response quality a22cf42

make streaming response 5ea073d

apply history flatten before it goint to prompt ef361b0

better management on system prompt 5f6306a

usue chat pipeline instead of model and tokenizer individually ac8e9cc

bugfix to padding-related issues f248fec

add attention mask b6b3940

Clean model description 4731160

pin torch to 2.4.0 4c6b4c5

enable zerogpu with decorator c5b2897

Apply ZeroGPU d181b45

switch to gradio version for stability reason a703203

add taiwan tinyllama 794ee70

Improve responsiveness by asynchronously retrieving web search context acda3f1

add llama 3.2 taiwan 3b b1544e2

add minicpm3 4b f5c0811

increase xt length to max 629495e

remove all moe fafc8cb

remove qwen 1.5 moe 6735035

adjust title style e9559bd

use another version of qwen 1.5 moe 96e60d6

add Qwen1.5-MoE e17afaf

Qwen2.5-MOE-6x1.5B 5eca666

remove under 3b models 617be26

user can define search timeout

e2ee907

give 5 second for web earch to gather reults

c00d442

support thinking models and streamingly display thought

8c3c2b9

do not preview prompt at error return from chat response

c09049b

inject assistant placeholder at right time

12dd3f3

disable L142 which is not needed

3c176a1

fix bug in prompt preview display

41ee8bf

add prompt preview for debug

5fc0117

fix: prevent self-talking issue by using tokenizer chat_template formatting

960db60

bugfix to Error: "str" object has no attribute "pad_token_id"

889f080

add taiwan elm 1.1b & 270m instruct

c8399e3

add type in qwen3 0.6b repo id

76d4d60

add qwen3

fe395ab

Add Smollm2 360m instruct fine-tuned on TaiwanChat

7308211

keep debug message

37f7787

add debug to show web resarch result

a2f07a4

give 1 second for web search to grab data

9ad3ffd

inject web search result if web search enabled

bc257ff

refactor(app): improve streaming, background search, dtype fallback, and cleanup :contentReference[oaicite:0]{index=0}

293686e

bugfixc: not using pipeline for response generation

939895d

Add original SmolLM2 135M Instruct for comparaison

423dc1a

Add SmolLM2-135M-Instruct-TaiwanChat

38fcc03

Add SmolLM2-135M TaiwanChat

0d642b7

default to gemma-3-4b

88a6a62

model repo_id typo fix

89372fa

enable web search by default

6235e63

remove tinyllama which has bad response quality

a22cf42

make streaming response

5ea073d

apply history flatten before it goint to prompt

ef361b0

better management on system prompt

5f6306a

usue chat pipeline instead of model and tokenizer individually

ac8e9cc

bugfix to padding-related issues

f248fec

add attention mask

b6b3940

Clean model description

4731160

pin torch to 2.4.0

4c6b4c5

enable zerogpu with decorator

c5b2897

Apply ZeroGPU

d181b45

switch to gradio version for stability reason

a703203

add taiwan tinyllama

794ee70

Improve responsiveness by asynchronously retrieving web search context

acda3f1

add llama 3.2 taiwan 3b

b1544e2

add minicpm3 4b

f5c0811

increase xt length to max

629495e

remove all moe

fafc8cb

remove qwen 1.5 moe

6735035

adjust title style

e9559bd

use another version of qwen 1.5 moe

96e60d6

add Qwen1.5-MoE

e17afaf

Qwen2.5-MOE-6x1.5B

5eca666

remove under 3b models

617be26