mljxy (Xiao Jin) – Community Activity

New activity in bartowski/DeepSeek-R1-Distill-Qwen-32B-GGUF 6 months ago

R1 32b is much worse than QwQ ...

22

#6 opened 7 months ago by

mirek190

New activity in TheBloke/openchat-3.5-0106-GGUF over 1 year ago

EOS token wrong

👍 2

4

#1 opened over 1 year ago by

mljxy

New activity in openchat/openchat-3.5-0106 over 1 year ago

Freezing Issue with gguf quant

5

#1 opened over 1 year ago by

dillfrescott

New activity in TheBloke/Starling-LM-7B-alpha-GGUF over 1 year ago

Tokenizer issue?

👍 5

27

#1 opened over 1 year ago by

sleepyjoecheated

New activity in Intel/neural-chat-7b-v3-1 over 1 year ago

Prompt Template?

👍 4

13

#1 opened over 1 year ago by

fakezeta

New activity in TheBloke/Nous-Capybara-34B-GGUF over 1 year ago

Incorrect EOS token

9

#2 opened over 1 year ago by

Henk717

New activity in TheBloke/dolphin-2_2-yi-34b-GGUF over 1 year ago

BOS token as 1 seriously hurts these GGUF Yi models

❤️ 2

29

#2 opened over 1 year ago by

wolfram

New activity in TheBloke/Yarn-Mistral-7B-128k-GGUF over 1 year ago

good parameters to run the model

5

#2 opened almost 2 years ago by

dzyla

New activity in TheBloke/openchat_3.5-GGUF almost 2 years ago

Prints only reply but when asked something extra it hangs

👍 1

14

#1 opened almost 2 years ago by

Pumba2

New activity in TheBloke/Falcon-180B-Chat-GGUF almost 2 years ago

error loading model: invalid character executing joined splited files

6

#12 opened almost 2 years ago by

Althenwolf

New activity in TheBloke/Spicyboros-70B-2.2-GGUF almost 2 years ago

spicyboros-70b-2.2.Q4_0.gguf broken as well?

10

#1 opened almost 2 years ago by

wolfram

New activity in TheBloke/guanaco-13B-GGML about 2 years ago

Prompt Format.

3

#1 opened about 2 years ago by

xzuyn

New activity in TheBloke/gpt4-alpaca-lora_mlp-65B-GGML about 2 years ago

8_0 Model and thank you so much for your work!!!

5

#2 opened about 2 years ago by deleted

New activity in eachadea/ggml-vicuna-13b-1.1 over 2 years ago

Optimal context to provide after tokenization change

1

#2 opened over 2 years ago by

IonizedLeaf

Xiao Jin

AI & ML interests

Organizations

R1 32b is much worse than QwQ ...

EOS token wrong

Freezing Issue with gguf quant

Tokenizer issue?

Prompt Template?

Incorrect EOS token

BOS token as 1 seriously hurts these GGUF Yi models

good parameters to run the model

Prints only reply but when asked something extra it hangs

error loading model: invalid character executing joined splited files

spicyboros-70b-2.2.Q4_0.gguf broken as well?

Prompt Format.

8_0 Model and thank you so much for your work!!!

Optimal context to provide after tokenization change

Xiao Jin

AI & ML interests

Organizations

mljxy's activity

R1 32b is much worse than QwQ ...

EOS token wrong

Freezing Issue with gguf quant

Tokenizer issue?

Prompt Template?

Incorrect EOS token

BOS token as 1 seriously hurts these GGUF Yi models

good parameters to run the model

Prints only reply but when asked something extra it hangs

error loading model: invalid character executing joined splited files

spicyboros-70b-2.2.Q4_0.gguf broken as well?

Prompt Format.

8_0 Model and thank you so much for your work!!!

Optimal context to provide after tokenization change