Junwon Hwang

nuxlear's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in LGAI-EXAONE/EXAONE-4.5-33B-FP8 11 days ago

text_config.layer_types has 65 entries but num_hidden_layers=64 — fails @strict config validation on load

❤️ 1

2

#1 opened 2 months ago by

appleparan

Fix text_config.layer_types length (65 -> 64) to match num_hidden_layers

#2 opened 2 months ago by

appleparan

New activity in LGAI-EXAONE/EXAONE-4.5-33B-GGUF 4 months ago

[Critical] Tensor Count Mismatch Error in EXAONE-4.5-33B GGUF Model

👍 1

2

#3 opened 4 months ago by

SGWon

llama.cpp

➕ 3

3

#1 opened 4 months ago by

blankreg

GGUF missing nextn tensors: embed_tokens and shared_head_head (llama.cpp fork fails to load)

👀 1

2

#2 opened 4 months ago by

miniwithmama

New activity in LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct 6 months ago

AttributeError: 'list' object has no attribute 'keys' on Mac M4

11

#9 opened 7 months ago by

Bias92

model.generate() crashes: AttributeError 'AttentionInterface' has no attribute 'get_interface' (transformers==5.0.0)

2

#11 opened 6 months ago by

Bias92

New activity in LGAI-EXAONE/K-EXAONE-236B-A23B 7 months ago

Do you have any plans to support NVFP4?

1

#14 opened 7 months ago by

taewan2002

Add HLE evaluation result

1

#11 opened 7 months ago by

burtenshaw

New activity in LGAI-EXAONE/EXAONE-3.5-2.4B-Instruct 7 months ago

Fix _tied_weights_keys mapping for Transformers v5

6

#10 opened 7 months ago by

Bias92

New activity in LGAI-EXAONE/K-EXAONE-236B-A23B 7 months ago

vllm inference error

1

#10 opened 7 months ago by

jujeongho

Tool-calling schema compliance check (repro steps + observed output)

3

#9 opened 7 months ago by

lesj0610

New activity in LGAI-EXAONE/K-EXAONE-236B-A23B 8 months ago

llama.cpp

2

#4 opened 8 months ago by

jacek2024

vllm `--reasoning-parser` option needs correction

2

#5 opened 8 months ago by

likejazz

New activity in LGAI-EXAONE/EXAONE-4.0-32B 9 months ago

Why does the EXAONE-4.0 chat_template strip <think> with [:9] instead of [:7]?

1

#13 opened 9 months ago by

kihunKim

New activity in LGAI-EXAONE/EXAONE-4.0-32B 10 months ago

question regarding the reasoning feature.

1

#12 opened 10 months ago by

wowohuhud

New activity in LGAI-EXAONE/EXAONE-4.0-32B about 1 year ago

Ollama Upload Plan

3

#9 opened about 1 year ago by

Timmothy

AWQ or GPTQ quantization?

2

#8 opened about 1 year ago by

lesj0610

New activity in LGAI-EXAONE/EXAONE-4.0-32B-GGUF about 1 year ago

update -ngl arg to count the output layer

1

#6 opened about 1 year ago by

owao

New activity in LGAI-EXAONE/EXAONE-4.0-1.2B-GGUF about 1 year ago

대체 뭘 만든건가요..

6

#2 opened about 1 year ago by

luckycontrol