Rayen

Lissanro's activity

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

New activity in zai-org/GLM-5 about 2 months ago

Please release a model with native 4-bit quantization

👀➕ 11

4

#4 opened about 2 months ago by

calycekr

New activity in ubergarm/Ling-1T-GGUF 5 months ago

128K context does not work (possibly because YaRN meta information is missing?)

➕ 1

2

#8 opened 5 months ago by

Lissanro

New activity in Jinx-org/Jinx-gpt-oss-20b-GGUF 7 months ago

MXFP4_MOE

🔥🚀 1

11

#1 opened 8 months ago by

marcelone

New activity in xai-org/grok-2 7 months ago

Incorrect Model Uploaded

🤗👍 18

6

#8 opened 7 months ago by

noteventhrice

New activity in deepseek-ai/DeepSeek-V3.1 8 months ago

Context length: is it 128K (as mentioned in the model card) or 160K (as specified in config.json)?

1

#17 opened 8 months ago by

Lissanro

New activity in tngtech/DeepSeek-R1T-Chimera 10 months ago

Any plans to release an updated version based on DeepSeek-V3-0526 + R1, or how to create the merge myself?

14

#4 opened 10 months ago by

Lissanro

New activity in bullerwins/DeepSeek-R1T-Chimera-GGUF 11 months ago

Please consider creating ik_llama.cpp compatible quants (without llama.cpp-specific MLA tensors)

1

#1 opened 11 months ago by

Lissanro

New activity in lynnea1517/c4ai-command-a-03-2025-exl2-4.5bpw-test about 1 year ago

chat_template.json is missing

2

#1 opened about 1 year ago by

Lissanro

New activity in llmixer/c4ai-command-a-03-2025-7.0bpw-h8-exl2 about 1 year ago

chat_template.json is missing

2

#1 opened about 1 year ago by

Lissanro

New activity in CohereLabs/c4ai-command-a-03-2025 about 1 year ago

Tell me how do you feel about this model without telling me how do you feel about this model

4

#5 opened about 1 year ago by

MrDevolver

New activity in Qwen/QwQ-32B about 1 year ago

Is this model native 128K context length, or YaRN extended?

7

#28 opened about 1 year ago by

danielhanchen

Doesn't Generate `<think>` tags

3

#25 opened about 1 year ago by

bingw5

New activity in turboderp/Llama-3-70B-Instruct-exl2 almost 2 years ago

tokenizer_config.json and config.json specify wrong EOS token, causing the model to not function correctly in backends which do not read EOS tokens from generation_config.json

🔥 1

6

#1 opened almost 2 years ago by

Lissanro

New activity in LoneStriker/Meta-Llama-3-8B-Instruct-8.0bpw-h8-exl2 almost 2 years ago

Works great on oobabooga, but always ends with assistant

1

#3 opened almost 2 years ago by

Noodlz

New activity in alpindale/WizardLM-2-8x22B almost 2 years ago

This could likely be dewokefied and possible even improved using mergekit's new 'Model Stock' method!

🔥 1

31

#5 opened almost 2 years ago by

jukofyork