mradermacher

/

model_requests

like 196

Qwen3.6-35B-A3B-abliterated-v4	0.00.031.154 E ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected
Qwen3.6-35B-A3B-abliterated-v4	0.00.037.048 I llama_completion: llama backend init
Qwen3.6-35B-A3B-abliterated-v4	0.00.037.055 I llama_completion: load the model and apply lora adapter, if any
Qwen3.6-35B-A3B-abliterated-v4	0.00.037.067 I common_init_result: fitting params to device memory ...
Qwen3.6-35B-A3B-abliterated-v4	0.00.037.071 I common_init_result: (for bugs during this step try to reproduce them with -fit off, or provide --verbose logs if the bug only occurs with -fit on)
Qwen3.6-35B-A3B-abliterated-v4	0.00.535.736 E llama_model_load: error loading model: missing tensor 'blk.40.attn_norm.weight'
Qwen3.6-35B-A3B-abliterated-v4	0.00.535.763 E llama_model_load_from_file_impl: failed to load model
Qwen3.6-35B-A3B-abliterated-v4	0.00.535.813 E common_fit_params: encountered an error while trying to fit params to free device memory: failed to load model
Qwen3.6-35B-A3B-abliterated-v4	0.00.612.343 W llama_model_loader: mmap is not supported for dry-run so it is now disabled
Qwen3.6-35B-A3B-abliterated-v4	0.00.995.151 E llama_model_load: error loading model: missing tensor 'blk.40.attn_norm.weight'
Qwen3.6-35B-A3B-abliterated-v4	0.00.995.174 E llama_model_load_from_file_impl: failed to load model
Qwen3.6-35B-A3B-abliterated-v4	0.00.995.186 E common_init_from_params: failed to load model 'Qwen3.6-35B-A3B-abliterated-v4.gguf~'
Qwen3.6-35B-A3B-abliterated-v4	0.00.995.191 E llama_completion: error: unable to create context
Qwen3.6-35B-A3B-abliterated-v4	+ echo 'dryrun failed'
Qwen3.6-35B-A3B-abliterated-v4	dryrun failed
Qwen3.6-35B-A3B-abliterated-v4	+ exit 57
Qwen3.6-35B-A3B-abliterated-v4	job finished, status 57
Qwen3.6-35B-A3B-abliterated-v4	job-done<0 Qwen3.6-35B-A3B-abliterated-v4 noquant 57>

Do you have any idea why @Bahushruth ?