qwp4w3hyb's picture

qwp4w3hyb PRO

qwp4w3hyb

·

AI & ML interests

<3 llama.cpp

Organizations

None yet

New activity in qwp4w3hyb/Hunyuan-A13B-Instruct-hf-WIP-GGUF 6 months ago

q4_k_s works and reads coherent but seems pretty stupid

#1 opened 6 months ago by

New activity in huggingface/InferenceSupport 6 months ago

baidu/ERNIE-4.5-VL-28B-A3B-PT

#3073 opened 6 months ago by

New activity in mistralai/Mistral-Small-3.1-24B-Instruct-2503 9 months ago

HF Format?

#2 opened 9 months ago by

New activity in qwp4w3hyb/Qwen2-72B-Instruct-iMat-GGUF over 1 year ago

Can you share your iMatrix file?

#1 opened over 1 year ago by

New activity in bartowski/Qwen2.5-Coder-7B-Instruct-GGUF over 1 year ago

FIM mode does not work properly, due to missing stop token

#3 opened over 1 year ago by

FIM with Ollama

#2 opened over 1 year ago by

New activity in qwp4w3hyb/Meta-Llama-3.1-8B-Instruct-iMat-GGUF over 1 year ago

The first GGUF that works with long context on llama.cpp!

#1 opened over 1 year ago by

New activity in open-llm-leaderboard/open_llm_leaderboard over 1 year ago

WizardLM-8x22B Evaluation failed

#823 opened over 1 year ago by

New activity in qwp4w3hyb/Llama-3-8B-Instruct-Gradient-1048k-iMat-GGUF over 1 year ago

70B version?

#2 opened over 1 year ago by

New activity in qwp4w3hyb/c4ai-command-r-plus-iMat-GGUF over 1 year ago

Update chat template

#1 opened over 1 year ago by

Will you re-upload these quants?

#2 opened over 1 year ago by

New activity in qwp4w3hyb/c4ai-command-r-v01-iMat-GGUF over 1 year ago

Update chat template

#2 opened over 1 year ago by

New activity in qwp4w3hyb/Meta-Llama-3-8B-Instruct-iMat-GGUF over 1 year ago

Update: iMatrix Wasn't The Cause Of The Hallucinations

#2 opened over 1 year ago by deleted

New activity in qwp4w3hyb/Llama-3-8B-Instruct-Gradient-1048k-iMat-GGUF over 1 year ago

New weights available

#1 opened over 1 year ago by

New activity in qwp4w3hyb/Meta-Llama-3-8B-Instruct-iMat-GGUF over 1 year ago

Thank you for the hint about fixing the eos_token_id

#1 opened over 1 year ago by

New activity in Vezora/Mistral-22B-v0.1 over 1 year ago

Base Model or Finetuned Version?

#2 opened over 1 year ago by

New activity in qwp4w3hyb/Qwen1.5-32B-Chat-iMat-GGUF over 1 year ago

Here is no IQ3_XXS Quant.

#1 opened over 1 year ago by

New activity in qwp4w3hyb/c4ai-command-r-v01-iMat-GGUF over 1 year ago

Requesting Q2_K and Q3_K_S

#1 opened over 1 year ago by

New activity in qwp4w3hyb/Qwen1.5-32B-Chat-iMat-GGUF over 1 year ago

Here is no IQ3_XXS Quant.

#1 opened over 1 year ago by