Hugging Face's logo
CR2022's picture
23 11

CR2022

CR2022
21world's profile picture sandropuppo's profile picture
·

AI & ML interests

Artificial Intelligence, Art, Experiments.

Organizations

None yet

CR2022's activity

New activity in bartowski/Qwen2.5-32B-Instruct-GGUF about 2 months ago

Qwen2.5-32B-Instruct-Q8_0.gguf Is hallucinating and talks to itself ignores whatever I write to it.

1
#4 opened about 2 months ago by CR2022
New activity in Karsh-CAI/Qwen2.5-32B-AGI-Q6_K-GGUF about 2 months ago

This quantization of the model hallucinates and talks to itself when you do even a simple Hello :) it ignores what you say in OpenWebui.
#2 opened about 2 months ago by CR2022

Can you or someone please quantize a Qwen2.5-32B-AGI-Q8_K-GGUF
#1 opened about 2 months ago by CR2022
New activity in TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF 11 months ago

WOW - best opensource llm I ever seen !

60
#1 opened 11 months ago by mirek190
New activity in TheBloke/Mixtral-8x7B-v0.1-GGUF 11 months ago

Does not work in latest oobabooga text generation web ui.

11
#7 opened 11 months ago by CR2022
New activity in TheBloke/openchat_3.5-GGUF about 1 year ago

These models that use rope behave very weird (dumb) with default settings of 32768 in latest Oobabooga text generation webui.

5
#6 opened about 1 year ago by CR2022
New activity in TheBloke/Yi-6B-200K-GGUF about 1 year ago

Can there be a 64K model? I have 128GB of system ram but this model is throwing errors in the latest text generation webui:

6
#1 opened about 1 year ago by CR2022
New activity in TheBloke/Yi-6B-GGUF about 1 year ago

finetuning from GGUF format?

8
#2 opened about 1 year ago by vasilee
New activity in impactframes/IF_PromptMKR_GPTQ about 1 year ago

IF_PromptMKR_GGML

3
#2 opened about 1 year ago by CR2022
New activity in TheBloke/WizardLM-7B-V1-0-Uncensored-SuperHOT-8K-GPTQ over 1 year ago

Traceback (most recent call last): File “/root/text-generation-webui/server.py”, line 68, in load_model_wrapper shared.model, shared.tokenizer
#1 opened over 1 year ago by CR2022
New activity in TheBloke/WizardLM-33B-V1.0-Uncensored-GGML over 1 year ago

IndexError: list index out of range

5
#1 opened over 1 year ago by CR2022

IndexError: list index out of range

5
#1 opened over 1 year ago by CR2022
New activity in TheBloke/WizardLM-30B-Uncensored-GGML over 1 year ago

error loading model: unrecognized tensor type 13

2
#3 opened over 1 year ago by CR2022
New activity in eachadea/ggml-vicuna-13b-1.1 over 1 year ago

uncensored version

8
#16 opened over 1 year ago by Feng7815
New activity in TheBloke/VicUnlocked-30B-LoRA-GGML over 1 year ago

OSError: models/VicUnlocked-30B-LoRA.ggml.q5_1 does not appear to have a file named config.json.

2
#5 opened over 1 year ago by CR2022

ERROR:Could not find the quantized model in .pt or .safetensors format, exiting...

1
#1 opened over 1 year ago by CR2022
New activity in liuhaotian/LLaVA-Lightning-MPT-7B-preview over 1 year ago

Quantized version?

2
#3 opened over 1 year ago by CR2022
New activity in TheBloke/wizardLM-7B-HF over 1 year ago

How to save fine-tuned model and load it again?

16
#2 opened over 1 year ago by gabriead
New activity in OccamRazor/mpt-7b-storywriter-4bit-128g over 1 year ago

Oobabooga cannot determine model type

17
#2 opened over 1 year ago by Dingus123

Gibberish output

6
#4 opened over 1 year ago by Coves