Bumba's picture

Bumba

Pumba2

·

AI & ML interests

None yet

Organizations

None yet

New activity in FinGPT/fingpt-forecaster_dow30_llama2-7b_lora 2 months ago

Anyone got GGUF ?

#14 opened 2 months ago by

New activity in unsloth/gemma-3-27b-it-GGUF 3 months ago

Google QAT is 17.2gb big?

#6 opened 3 months ago by

New activity in unsloth/gemma-3-12b-it-GGUF 3 months ago

Model bigger than regular Q4_K_M. What is the difference then ? (GGUF v2.0)

#6 opened 3 months ago by

Model fails to load on LM Studio

#5 opened 3 months ago by

New activity in lmstudio-community/gemma-3-12B-it-qat-GGUF 3 months ago

No difference in size ?

#2 opened 3 months ago by

New activity in google/gemma-3-12b-it-qat-q4_0-gguf 3 months ago

Error loading model in LM Studio - 0.3.15 (Build 3)

#1 opened 3 months ago by

New activity in microsoft/Phi-3-small-8k-instruct about 1 year ago

GGUF version?

#9 opened about 1 year ago by

New activity in snorkelai/Snorkel-Mistral-PairRM-DPO over 1 year ago

one gguf model

#2 opened over 1 year ago by

andrew-cartwheel

New activity in TomGrc/FusionNet_7Bx2_MoE_14B over 1 year ago

GGUF Version

#1 opened over 1 year ago by

New activity in TheBloke/phi-2-GGUF over 1 year ago

today's version of llama.cpp results in an error

#4 opened over 1 year ago by

New activity in TheBloke/phi-2-GPTQ over 1 year ago

No GGUF ?

#2 opened over 1 year ago by

New activity in TheBloke/openchat-3.5-1210-GGUF over 1 year ago

Sorta Broken

#1 opened over 1 year ago by

New activity in TheBloke/Magicoder-S-DS-6.7B-GGUF over 1 year ago

failed to load the model

#1 opened over 1 year ago by

New activity in TheBloke/XwinCoder-13B-GGUF over 1 year ago

Any chance of releasing quantized 7b ver ?

#1 opened over 1 year ago by

New activity in TheBloke/openchat_3.5-GGUF over 1 year ago

Prints only reply but when asked something extra it hangs

#1 opened over 1 year ago by

New activity in TheBloke/deepseek-coder-1.3b-instruct-GGUF over 1 year ago

Crashes or generates gibberish

#1 opened over 1 year ago by

New activity in openchat/openchat_3.5 over 1 year ago

Great. Now make 128k version like they done with Mistral lately : )

#8 opened over 1 year ago by

New activity in TheBloke/Nous-Capybara-3B-v1.9-GPTQ over 1 year ago

Why only as GPTQ and not as GGUF as well ?

#1 opened over 1 year ago by

New activity in TheBloke/zephyr-7B-beta-GGUF over 1 year ago

Possible Loading Error with GPT4All

#1 opened over 1 year ago by deleted

New activity in Nondzu/Mistral-7B-code-16k-qlora over 1 year ago

Human Eval and Human Eval-X score?

#2 opened over 1 year ago by