Text Generation
Transformers
Safetensors
English
llama
causal-lm
text-generation-inference
4-bit precision

Unable to load it using --pre_layer flag

#5
by boricuapab - opened

Starting the web UI...
Gradio HTTP request redirected to localhost :)
Loading TheBloke_stable-vicuna-13B-GPTQ...
Found the following quantized model: models\TheBloke_stable-vicuna-13B-GPTQ\stable-vicuna-13B-GPTQ-4bit.compat.no-act-order.safetensors
Loading model ...
Traceback (most recent call last):
File "C:\oobaBoo\oobabooga-windows\text-generation-webui\server.py", line 914, in
shared.model, shared.tokenizer = load_model(shared.model_name)
File "C:\oobaBoo\oobabooga-windows\text-generation-webui\modules\models.py", line 158, in load_model
model = load_quantized(model_name)
File "C:\oobaBoo\oobabooga-windows\text-generation-webui\modules\GPTQ_loader.py", line 173, in load_quantized
model = load_quant(str(path_to_model), str(pt_path), shared.args.wbits, shared.args.groupsize, shared.args.pre_layer)
File "C:\oobaBoo\oobabooga-windows\text-generation-webui\repositories\GPTQ-for-LLaMa\llama_inference_offload.py", line 226, in load_quant
model.load_state_dict(safe_load(checkpoint))
File "C:\oobaBoo\oobabooga-windows\installer_files\env\lib\site-packages\torch\nn\modules\module.py", line 2041, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for LlamaForCausalLM:
Missing key(s) in state_dict: "model.layers.0.self_attn.k_proj.bias", "model.layers.0.self_attn.o_proj.bias", "model.layers.0.self_attn.q_proj.bias", "model.layers.0.self_attn.v_proj.bias", "model.layers.0.mlp.down_proj.bias", "model.layers.0.mlp.gate_proj.bias", "model.layers.0.mlp.up_proj.bias", "model.layers.1.self_attn.k_proj.bias", "model.layers.1.self_attn.o_proj.bias", "model.layers.1.self_attn.q_proj.bias", "model.layers.1.self_attn.v_proj.bias", "model.layers.1.mlp.down_proj.bias", "model.layers.1.mlp.gate_proj.bias", "model.layers.1.mlp.up_proj.bias", "model.layers.2.self_attn.k_proj.bias", "model.layers.2.self_attn.o_proj.bias", "model.layers.2.self_attn.q_proj.bias", "model.layers.2.self_attn.v_proj.bias", "model.layers.2.mlp.down_proj.bias", "model.layers.2.mlp.gate_proj.bias", "model.layers.2.mlp.up_proj.bias", "model.layers.3.self_attn.k_proj.bias", "model.layers.3.self_attn.o_proj.bias", "model.layers.3.self_attn.q_proj.bias", "model.layers.3.self_attn.v_proj.bias", "model.layers.3.mlp.down_proj.bias", "model.layers.3.mlp.gate_proj.bias", "model.layers.3.mlp.up_proj.bias", "model.layers.4.self_attn.k_proj.bias", "model.layers.4.self_attn.o_proj.bias", "model.layers.4.self_attn.q_proj.bias", "model.layers.4.self_attn.v_proj.bias", "model.layers.4.mlp.down_proj.bias", "model.layers.4.mlp.gate_proj.bias", "model.layers.4.mlp.up_proj.bias", "model.layers.5.self_attn.k_proj.bias", "model.layers.5.self_attn.o_proj.bias", "model.layers.5.self_attn.q_proj.bias", "model.layers.5.self_attn.v_proj.bias", "model.layers.5.mlp.down_proj.bias", "model.layers.5.mlp.gate_proj.bias", "model.layers.5.mlp.up_proj.bias", "model.layers.6.self_attn.k_proj.bias", "model.layers.6.self_attn.o_proj.bias", "model.layers.6.self_attn.q_proj.bias", "model.layers.6.self_attn.v_proj.bias", "model.layers.6.mlp.down_proj.bias", "model.layers.6.mlp.gate_proj.bias", "model.layers.6.mlp.up_proj.bias", "model.layers.7.self_attn.k_proj.bias", "model.layers.7.self_attn.o_proj.bias", "model.layers.7.self_attn.q_proj.bias", "model.layers.7.self_attn.v_proj.bias", "model.layers.7.mlp.down_proj.bias", "model.layers.7.mlp.gate_proj.bias", "model.layers.7.mlp.up_proj.bias", "model.layers.8.self_attn.k_proj.bias", "model.layers.8.self_attn.o_proj.bias", "model.layers.8.self_attn.q_proj.bias", "model.layers.8.self_attn.v_proj.bias", "model.layers.8.mlp.down_proj.bias", "model.layers.8.mlp.gate_proj.bias", "model.layers.8.mlp.up_proj.bias", "model.layers.9.self_attn.k_proj.bias", "model.layers.9.self_attn.o_proj.bias", "model.layers.9.self_attn.q_proj.bias", "model.layers.9.self_attn.v_proj.bias", "model.layers.9.mlp.down_proj.bias", "model.layers.9.mlp.gate_proj.bias", "model.layers.9.mlp.up_proj.bias", "model.layers.10.self_attn.k_proj.bias", "model.layers.10.self_attn.o_proj.bias", "model.layers.10.self_attn.q_proj.bias", "model.layers.10.self_attn.v_proj.bias", "model.layers.10.mlp.down_proj.bias", "model.layers.10.mlp.gate_proj.bias", "model.layers.10.mlp.up_proj.bias", "model.layers.11.self_attn.k_proj.bias", "model.layers.11.self_attn.o_proj.bias", "model.layers.11.self_attn.q_proj.bias", "model.layers.11.self_attn.v_proj.bias", "model.layers.11.mlp.down_proj.bias", "model.layers.11.mlp.gate_proj.bias", "model.layers.11.mlp.up_proj.bias", "model.layers.12.self_attn.k_proj.bias", "model.layers.12.self_attn.o_proj.bias", "model.layers.12.self_attn.q_proj.bias", "model.layers.12.self_attn.v_proj.bias", "model.layers.12.mlp.down_proj.bias", "model.layers.12.mlp.gate_proj.bias", "model.layers.12.mlp.up_proj.bias", "model.layers.13.self_attn.k_proj.bias", "model.layers.13.self_attn.o_proj.bias", "model.layers.13.self_attn.q_proj.bias", "model.layers.13.self_attn.v_proj.bias", "model.layers.13.mlp.down_proj.bias", "model.layers.13.mlp.gate_proj.bias", "model.layers.13.mlp.up_proj.bias", "model.layers.14.self_attn.k_proj.bias", "model.layers.14.self_attn.o_proj.bias", "model.layers.14.self_attn.q_proj.bias", "model.layers.14.self_attn.v_proj.bias", "model.layers.14.mlp.down_proj.bias", "model.layers.14.mlp.gate_proj.bias", "model.layers.14.mlp.up_proj.bias", "model.layers.15.self_attn.k_proj.bias", "model.layers.15.self_attn.o_proj.bias", "model.layers.15.self_attn.q_proj.bias", "model.layers.15.self_attn.v_proj.bias", "model.layers.15.mlp.down_proj.bias", "model.layers.15.mlp.gate_proj.bias", "model.layers.15.mlp.up_proj.bias", "model.layers.16.self_attn.k_proj.bias", "model.layers.16.self_attn.o_proj.bias", "model.layers.16.self_attn.q_proj.bias", "model.layers.16.self_attn.v_proj.bias", "model.layers.16.mlp.down_proj.bias", "model.layers.16.mlp.gate_proj.bias", "model.layers.16.mlp.up_proj.bias", "model.layers.17.self_attn.k_proj.bias", "model.layers.17.self_attn.o_proj.bias", "model.layers.17.self_attn.q_proj.bias", "model.layers.17.self_attn.v_proj.bias", "model.layers.17.mlp.down_proj.bias", "model.layers.17.mlp.gate_proj.bias", "model.layers.17.mlp.up_proj.bias", "model.layers.18.self_attn.k_proj.bias", "model.layers.18.self_attn.o_proj.bias", "model.layers.18.self_attn.q_proj.bias", "model.layers.18.self_attn.v_proj.bias", "model.layers.18.mlp.down_proj.bias", "model.layers.18.mlp.gate_proj.bias", "model.layers.18.mlp.up_proj.bias", "model.layers.19.self_attn.k_proj.bias", "model.layers.19.self_attn.o_proj.bias", "model.layers.19.self_attn.q_proj.bias", "model.layers.19.self_attn.v_proj.bias", "model.layers.19.mlp.down_proj.bias", "model.layers.19.mlp.gate_proj.bias", "model.layers.19.mlp.up_proj.bias", "model.layers.20.self_attn.k_proj.bias", "model.layers.20.self_attn.o_proj.bias", "model.layers.20.self_attn.q_proj.bias", "model.layers.20.self_attn.v_proj.bias", "model.layers.20.mlp.down_proj.bias", "model.layers.20.mlp.gate_proj.bias", "model.layers.20.mlp.up_proj.bias", "model.layers.21.self_attn.k_proj.bias", "model.layers.21.self_attn.o_proj.bias", "model.layers.21.self_attn.q_proj.bias", "model.layers.21.self_attn.v_proj.bias", "model.layers.21.mlp.down_proj.bias", "model.layers.21.mlp.gate_proj.bias", "model.layers.21.mlp.up_proj.bias", "model.layers.22.self_attn.k_proj.bias", "model.layers.22.self_attn.o_proj.bias", "model.layers.22.self_attn.q_proj.bias", "model.layers.22.self_attn.v_proj.bias", "model.layers.22.mlp.down_proj.bias", "model.layers.22.mlp.gate_proj.bias", "model.layers.22.mlp.up_proj.bias", "model.layers.23.self_attn.k_proj.bias", "model.layers.23.self_attn.o_proj.bias", "model.layers.23.self_attn.q_proj.bias", "model.layers.23.self_attn.v_proj.bias", "model.layers.23.mlp.down_proj.bias", "model.layers.23.mlp.gate_proj.bias", "model.layers.23.mlp.up_proj.bias", "model.layers.24.self_attn.k_proj.bias", "model.layers.24.self_attn.o_proj.bias", "model.layers.24.self_attn.q_proj.bias", "model.layers.24.self_attn.v_proj.bias", "model.layers.24.mlp.down_proj.bias", "model.layers.24.mlp.gate_proj.bias", "model.layers.24.mlp.up_proj.bias", "model.layers.25.self_attn.k_proj.bias", "model.layers.25.self_attn.o_proj.bias", "model.layers.25.self_attn.q_proj.bias", "model.layers.25.self_attn.v_proj.bias", "model.layers.25.mlp.down_proj.bias", "model.layers.25.mlp.gate_proj.bias", "model.layers.25.mlp.up_proj.bias", "model.layers.26.self_attn.k_proj.bias", "model.layers.26.self_attn.o_proj.bias", "model.layers.26.self_attn.q_proj.bias", "model.layers.26.self_attn.v_proj.bias", "model.layers.26.mlp.down_proj.bias", "model.layers.26.mlp.gate_proj.bias", "model.layers.26.mlp.up_proj.bias", "model.layers.27.self_attn.k_proj.bias", "model.layers.27.self_attn.o_proj.bias", "model.layers.27.self_attn.q_proj.bias", "model.layers.27.self_attn.v_proj.bias", "model.layers.27.mlp.down_proj.bias", "model.layers.27.mlp.gate_proj.bias", "model.layers.27.mlp.up_proj.bias", "model.layers.28.self_attn.k_proj.bias", "model.layers.28.self_attn.o_proj.bias", "model.layers.28.self_attn.q_proj.bias", "model.layers.28.self_attn.v_proj.bias", "model.layers.28.mlp.down_proj.bias", "model.layers.28.mlp.gate_proj.bias", "model.layers.28.mlp.up_proj.bias", "model.layers.29.self_attn.k_proj.bias", "model.layers.29.self_attn.o_proj.bias", "model.layers.29.self_attn.q_proj.bias", "model.layers.29.self_attn.v_proj.bias", "model.layers.29.mlp.down_proj.bias", "model.layers.29.mlp.gate_proj.bias", "model.layers.29.mlp.up_proj.bias", "model.layers.30.self_attn.k_proj.bias", "model.layers.30.self_attn.o_proj.bias", "model.layers.30.self_attn.q_proj.bias", "model.layers.30.self_attn.v_proj.bias", "model.layers.30.mlp.down_proj.bias", "model.layers.30.mlp.gate_proj.bias", "model.layers.30.mlp.up_proj.bias", "model.layers.31.self_attn.k_proj.bias", "model.layers.31.self_attn.o_proj.bias", "model.layers.31.self_attn.q_proj.bias", "model.layers.31.self_attn.v_proj.bias", "model.layers.31.mlp.down_proj.bias", "model.layers.31.mlp.gate_proj.bias", "model.layers.31.mlp.up_proj.bias", "model.layers.32.self_attn.k_proj.bias", "model.layers.32.self_attn.o_proj.bias", "model.layers.32.self_attn.q_proj.bias", "model.layers.32.self_attn.v_proj.bias", "model.layers.32.mlp.down_proj.bias", "model.layers.32.mlp.gate_proj.bias", "model.layers.32.mlp.up_proj.bias", "model.layers.33.self_attn.k_proj.bias", "model.layers.33.self_attn.o_proj.bias", "model.layers.33.self_attn.q_proj.bias", "model.layers.33.self_attn.v_proj.bias", "model.layers.33.mlp.down_proj.bias", "model.layers.33.mlp.gate_proj.bias", "model.layers.33.mlp.up_proj.bias", "model.layers.34.self_attn.k_proj.bias", "model.layers.34.self_attn.o_proj.bias", "model.layers.34.self_attn.q_proj.bias", "model.layers.34.self_attn.v_proj.bias", "model.layers.34.mlp.down_proj.bias", "model.layers.34.mlp.gate_proj.bias", "model.layers.34.mlp.up_proj.bias", "model.layers.35.self_attn.k_proj.bias", "model.layers.35.self_attn.o_proj.bias", "model.layers.35.self_attn.q_proj.bias", "model.layers.35.self_attn.v_proj.bias", "model.layers.35.mlp.down_proj.bias", "model.layers.35.mlp.gate_proj.bias", "model.layers.35.mlp.up_proj.bias", "model.layers.36.self_attn.k_proj.bias", "model.layers.36.self_attn.o_proj.bias", "model.layers.36.self_attn.q_proj.bias", "model.layers.36.self_attn.v_proj.bias", "model.layers.36.mlp.down_proj.bias", "model.layers.36.mlp.gate_proj.bias", "model.layers.36.mlp.up_proj.bias", "model.layers.37.self_attn.k_proj.bias", "model.layers.37.self_attn.o_proj.bias", "model.layers.37.self_attn.q_proj.bias", "model.layers.37.self_attn.v_proj.bias", "model.layers.37.mlp.down_proj.bias", "model.layers.37.mlp.gate_proj.bias", "model.layers.37.mlp.up_proj.bias", "model.layers.38.self_attn.k_proj.bias", "model.layers.38.self_attn.o_proj.bias", "model.layers.38.self_attn.q_proj.bias", "model.layers.38.self_attn.v_proj.bias", "model.layers.38.mlp.down_proj.bias", "model.layers.38.mlp.gate_proj.bias", "model.layers.38.mlp.up_proj.bias", "model.layers.39.self_attn.k_proj.bias", "model.layers.39.self_attn.o_proj.bias", "model.layers.39.self_attn.q_proj.bias", "model.layers.39.self_attn.v_proj.bias", "model.layers.39.mlp.down_proj.bias", "model.layers.39.mlp.gate_proj.bias", "model.layers.39.mlp.up_proj.bias".
Unexpected key(s) in state_dict: "model.layers.0.self_attn.k_proj.g_idx", "model.layers.0.self_attn.o_proj.g_idx", "model.layers.0.self_attn.q_proj.g_idx", "model.layers.0.self_attn.v_proj.g_idx", "model.layers.0.mlp.down_proj.g_idx", "model.layers.0.mlp.gate_proj.g_idx", "model.layers.0.mlp.up_proj.g_idx", "model.layers.1.self_attn.k_proj.g_idx", "model.layers.1.self_attn.o_proj.g_idx", "model.layers.1.self_attn.q_proj.g_idx", "model.layers.1.self_attn.v_proj.g_idx", "model.layers.1.mlp.down_proj.g_idx", "model.layers.1.mlp.gate_proj.g_idx", "model.layers.1.mlp.up_proj.g_idx", "model.layers.2.self_attn.k_proj.g_idx", "model.layers.2.self_attn.o_proj.g_idx", "model.layers.2.self_attn.q_proj.g_idx", "model.layers.2.self_attn.v_proj.g_idx", "model.layers.2.mlp.down_proj.g_idx", "model.layers.2.mlp.gate_proj.g_idx", "model.layers.2.mlp.up_proj.g_idx", "model.layers.3.self_attn.k_proj.g_idx", "model.layers.3.self_attn.o_proj.g_idx", "model.layers.3.self_attn.q_proj.g_idx", "model.layers.3.self_attn.v_proj.g_idx", "model.layers.3.mlp.down_proj.g_idx", "model.layers.3.mlp.gate_proj.g_idx", "model.layers.3.mlp.up_proj.g_idx", "model.layers.4.self_attn.k_proj.g_idx", "model.layers.4.self_attn.o_proj.g_idx", "model.layers.4.self_attn.q_proj.g_idx", "model.layers.4.self_attn.v_proj.g_idx", "model.layers.4.mlp.down_proj.g_idx", "model.layers.4.mlp.gate_proj.g_idx", "model.layers.4.mlp.up_proj.g_idx", "model.layers.5.self_attn.k_proj.g_idx", "model.layers.5.self_attn.o_proj.g_idx", "model.layers.5.self_attn.q_proj.g_idx", "model.layers.5.self_attn.v_proj.g_idx", "model.layers.5.mlp.down_proj.g_idx", "model.layers.5.mlp.gate_proj.g_idx", "model.layers.5.mlp.up_proj.g_idx", "model.layers.6.self_attn.k_proj.g_idx", "model.layers.6.self_attn.o_proj.g_idx", "model.layers.6.self_attn.q_proj.g_idx", "model.layers.6.self_attn.v_proj.g_idx", "model.layers.6.mlp.down_proj.g_idx", "model.layers.6.mlp.gate_proj.g_idx", "model.layers.6.mlp.up_proj.g_idx", "model.layers.7.self_attn.k_proj.g_idx", "model.layers.7.self_attn.o_proj.g_idx", "model.layers.7.self_attn.q_proj.g_idx", "model.layers.7.self_attn.v_proj.g_idx", "model.layers.7.mlp.down_proj.g_idx", "model.layers.7.mlp.gate_proj.g_idx", "model.layers.7.mlp.up_proj.g_idx", "model.layers.8.self_attn.k_proj.g_idx", "model.layers.8.self_attn.o_proj.g_idx", "model.layers.8.self_attn.q_proj.g_idx", "model.layers.8.self_attn.v_proj.g_idx", "model.layers.8.mlp.down_proj.g_idx", "model.layers.8.mlp.gate_proj.g_idx", "model.layers.8.mlp.up_proj.g_idx", "model.layers.9.self_attn.k_proj.g_idx", "model.layers.9.self_attn.o_proj.g_idx", "model.layers.9.self_attn.q_proj.g_idx", "model.layers.9.self_attn.v_proj.g_idx", "model.layers.9.mlp.down_proj.g_idx", "model.layers.9.mlp.gate_proj.g_idx", "model.layers.9.mlp.up_proj.g_idx", "model.layers.10.self_attn.k_proj.g_idx", "model.layers.10.self_attn.o_proj.g_idx", "model.layers.10.self_attn.q_proj.g_idx", "model.layers.10.self_attn.v_proj.g_idx", "model.layers.10.mlp.down_proj.g_idx", "model.layers.10.mlp.gate_proj.g_idx", "model.layers.10.mlp.up_proj.g_idx", "model.layers.11.self_attn.k_proj.g_idx", "model.layers.11.self_attn.o_proj.g_idx", "model.layers.11.self_attn.q_proj.g_idx", "model.layers.11.self_attn.v_proj.g_idx", "model.layers.11.mlp.down_proj.g_idx", "model.layers.11.mlp.gate_proj.g_idx", "model.layers.11.mlp.up_proj.g_idx", "model.layers.12.self_attn.k_proj.g_idx", "model.layers.12.self_attn.o_proj.g_idx", "model.layers.12.self_attn.q_proj.g_idx", "model.layers.12.self_attn.v_proj.g_idx", "model.layers.12.mlp.down_proj.g_idx", "model.layers.12.mlp.gate_proj.g_idx", "model.layers.12.mlp.up_proj.g_idx", "model.layers.13.self_attn.k_proj.g_idx", "model.layers.13.self_attn.o_proj.g_idx", "model.layers.13.self_attn.q_proj.g_idx", "model.layers.13.self_attn.v_proj.g_idx", "model.layers.13.mlp.down_proj.g_idx", "model.layers.13.mlp.gate_proj.g_idx", "model.layers.13.mlp.up_proj.g_idx", "model.layers.14.self_attn.k_proj.g_idx", "model.layers.14.self_attn.o_proj.g_idx", "model.layers.14.self_attn.q_proj.g_idx", "model.layers.14.self_attn.v_proj.g_idx", "model.layers.14.mlp.down_proj.g_idx", "model.layers.14.mlp.gate_proj.g_idx", "model.layers.14.mlp.up_proj.g_idx", "model.layers.15.self_attn.k_proj.g_idx", "model.layers.15.self_attn.o_proj.g_idx", "model.layers.15.self_attn.q_proj.g_idx", "model.layers.15.self_attn.v_proj.g_idx", "model.layers.15.mlp.down_proj.g_idx", "model.layers.15.mlp.gate_proj.g_idx", "model.layers.15.mlp.up_proj.g_idx", "model.layers.16.self_attn.k_proj.g_idx", "model.layers.16.self_attn.o_proj.g_idx", "model.layers.16.self_attn.q_proj.g_idx", "model.layers.16.self_attn.v_proj.g_idx", "model.layers.16.mlp.down_proj.g_idx", "model.layers.16.mlp.gate_proj.g_idx", "model.layers.16.mlp.up_proj.g_idx", "model.layers.17.self_attn.k_proj.g_idx", "model.layers.17.self_attn.o_proj.g_idx", "model.layers.17.self_attn.q_proj.g_idx", "model.layers.17.self_attn.v_proj.g_idx", "model.layers.17.mlp.down_proj.g_idx", "model.layers.17.mlp.gate_proj.g_idx", "model.layers.17.mlp.up_proj.g_idx", "model.layers.18.self_attn.k_proj.g_idx", "model.layers.18.self_attn.o_proj.g_idx", "model.layers.18.self_attn.q_proj.g_idx", "model.layers.18.self_attn.v_proj.g_idx", "model.layers.18.mlp.down_proj.g_idx", "model.layers.18.mlp.gate_proj.g_idx", "model.layers.18.mlp.up_proj.g_idx", "model.layers.19.self_attn.k_proj.g_idx", "model.layers.19.self_attn.o_proj.g_idx", "model.layers.19.self_attn.q_proj.g_idx", "model.layers.19.self_attn.v_proj.g_idx", "model.layers.19.mlp.down_proj.g_idx", "model.layers.19.mlp.gate_proj.g_idx", "model.layers.19.mlp.up_proj.g_idx", "model.layers.20.self_attn.k_proj.g_idx", "model.layers.20.self_attn.o_proj.g_idx", "model.layers.20.self_attn.q_proj.g_idx", "model.layers.20.self_attn.v_proj.g_idx", "model.layers.20.mlp.down_proj.g_idx", "model.layers.20.mlp.gate_proj.g_idx", "model.layers.20.mlp.up_proj.g_idx", "model.layers.21.self_attn.k_proj.g_idx", "model.layers.21.self_attn.o_proj.g_idx", "model.layers.21.self_attn.q_proj.g_idx", "model.layers.21.self_attn.v_proj.g_idx", "model.layers.21.mlp.down_proj.g_idx", "model.layers.21.mlp.gate_proj.g_idx", "model.layers.21.mlp.up_proj.g_idx", "model.layers.22.self_attn.k_proj.g_idx", "model.layers.22.self_attn.o_proj.g_idx", "model.layers.22.self_attn.q_proj.g_idx", "model.layers.22.self_attn.v_proj.g_idx", "model.layers.22.mlp.down_proj.g_idx", "model.layers.22.mlp.gate_proj.g_idx", "model.layers.22.mlp.up_proj.g_idx", "model.layers.23.self_attn.k_proj.g_idx", "model.layers.23.self_attn.o_proj.g_idx", "model.layers.23.self_attn.q_proj.g_idx", "model.layers.23.self_attn.v_proj.g_idx", "model.layers.23.mlp.down_proj.g_idx", "model.layers.23.mlp.gate_proj.g_idx", "model.layers.23.mlp.up_proj.g_idx", "model.layers.24.self_attn.k_proj.g_idx", "model.layers.24.self_attn.o_proj.g_idx", "model.layers.24.self_attn.q_proj.g_idx", "model.layers.24.self_attn.v_proj.g_idx", "model.layers.24.mlp.down_proj.g_idx", "model.layers.24.mlp.gate_proj.g_idx", "model.layers.24.mlp.up_proj.g_idx", "model.layers.25.self_attn.k_proj.g_idx", "model.layers.25.self_attn.o_proj.g_idx", "model.layers.25.self_attn.q_proj.g_idx", "model.layers.25.self_attn.v_proj.g_idx", "model.layers.25.mlp.down_proj.g_idx", "model.layers.25.mlp.gate_proj.g_idx", "model.layers.25.mlp.up_proj.g_idx", "model.layers.26.self_attn.k_proj.g_idx", "model.layers.26.self_attn.o_proj.g_idx", "model.layers.26.self_attn.q_proj.g_idx", "model.layers.26.self_attn.v_proj.g_idx", "model.layers.26.mlp.down_proj.g_idx", "model.layers.26.mlp.gate_proj.g_idx", "model.layers.26.mlp.up_proj.g_idx", "model.layers.27.self_attn.k_proj.g_idx", "model.layers.27.self_attn.o_proj.g_idx", "model.layers.27.self_attn.q_proj.g_idx", "model.layers.27.self_attn.v_proj.g_idx", "model.layers.27.mlp.down_proj.g_idx", "model.layers.27.mlp.gate_proj.g_idx", "model.layers.27.mlp.up_proj.g_idx", "model.layers.28.self_attn.k_proj.g_idx", "model.layers.28.self_attn.o_proj.g_idx", "model.layers.28.self_attn.q_proj.g_idx", "model.layers.28.self_attn.v_proj.g_idx", "model.layers.28.mlp.down_proj.g_idx", "model.layers.28.mlp.gate_proj.g_idx", "model.layers.28.mlp.up_proj.g_idx", "model.layers.29.self_attn.k_proj.g_idx", "model.layers.29.self_attn.o_proj.g_idx", "model.layers.29.self_attn.q_proj.g_idx", "model.layers.29.self_attn.v_proj.g_idx", "model.layers.29.mlp.down_proj.g_idx", "model.layers.29.mlp.gate_proj.g_idx", "model.layers.29.mlp.up_proj.g_idx", "model.layers.30.self_attn.k_proj.g_idx", "model.layers.30.self_attn.o_proj.g_idx", "model.layers.30.self_attn.q_proj.g_idx", "model.layers.30.self_attn.v_proj.g_idx", "model.layers.30.mlp.down_proj.g_idx", "model.layers.30.mlp.gate_proj.g_idx", "model.layers.30.mlp.up_proj.g_idx", "model.layers.31.self_attn.k_proj.g_idx", "model.layers.31.self_attn.o_proj.g_idx", "model.layers.31.self_attn.q_proj.g_idx", "model.layers.31.self_attn.v_proj.g_idx", "model.layers.31.mlp.down_proj.g_idx", "model.layers.31.mlp.gate_proj.g_idx", "model.layers.31.mlp.up_proj.g_idx", "model.layers.32.self_attn.k_proj.g_idx", "model.layers.32.self_attn.o_proj.g_idx", "model.layers.32.self_attn.q_proj.g_idx", "model.layers.32.self_attn.v_proj.g_idx", "model.layers.32.mlp.down_proj.g_idx", "model.layers.32.mlp.gate_proj.g_idx", "model.layers.32.mlp.up_proj.g_idx", "model.layers.33.self_attn.k_proj.g_idx", "model.layers.33.self_attn.o_proj.g_idx", "model.layers.33.self_attn.q_proj.g_idx", "model.layers.33.self_attn.v_proj.g_idx", "model.layers.33.mlp.down_proj.g_idx", "model.layers.33.mlp.gate_proj.g_idx", "model.layers.33.mlp.up_proj.g_idx", "model.layers.34.self_attn.k_proj.g_idx", "model.layers.34.self_attn.o_proj.g_idx", "model.layers.34.self_attn.q_proj.g_idx", "model.layers.34.self_attn.v_proj.g_idx", "model.layers.34.mlp.down_proj.g_idx", "model.layers.34.mlp.gate_proj.g_idx", "model.layers.34.mlp.up_proj.g_idx", "model.layers.35.self_attn.k_proj.g_idx", "model.layers.35.self_attn.o_proj.g_idx", "model.layers.35.self_attn.q_proj.g_idx", "model.layers.35.self_attn.v_proj.g_idx", "model.layers.35.mlp.down_proj.g_idx", "model.layers.35.mlp.gate_proj.g_idx", "model.layers.35.mlp.up_proj.g_idx", "model.layers.36.self_attn.k_proj.g_idx", "model.layers.36.self_attn.o_proj.g_idx", "model.layers.36.self_attn.q_proj.g_idx", "model.layers.36.self_attn.v_proj.g_idx", "model.layers.36.mlp.down_proj.g_idx", "model.layers.36.mlp.gate_proj.g_idx", "model.layers.36.mlp.up_proj.g_idx", "model.layers.37.self_attn.k_proj.g_idx", "model.layers.37.self_attn.o_proj.g_idx", "model.layers.37.self_attn.q_proj.g_idx", "model.layers.37.self_attn.v_proj.g_idx", "model.layers.37.mlp.down_proj.g_idx", "model.layers.37.mlp.gate_proj.g_idx", "model.layers.37.mlp.up_proj.g_idx", "model.layers.38.self_attn.k_proj.g_idx", "model.layers.38.self_attn.o_proj.g_idx", "model.layers.38.self_attn.q_proj.g_idx", "model.layers.38.self_attn.v_proj.g_idx", "model.layers.38.mlp.down_proj.g_idx", "model.layers.38.mlp.gate_proj.g_idx", "model.layers.38.mlp.up_proj.g_idx", "model.layers.39.self_attn.k_proj.g_idx", "model.layers.39.self_attn.o_proj.g_idx", "model.layers.39.self_attn.q_proj.g_idx", "model.layers.39.self_attn.v_proj.g_idx", "model.layers.39.mlp.down_proj.g_idx", "model.layers.39.mlp.gate_proj.g_idx", "model.layers.39.mlp.up_proj.g_idx".
Press any key to continue . . .

Yeah I've had this issue reported before. It may be a bug in the GPTQ code or in text-gen-ui.

Are there GPTQ models I've made that do work with pre_layer?

Tried using --pre_layer with your wizard lm models but it wouldn't load in oobabooga either. I have been able to use your stable lm ggml through both llamacpp and oobabooga. Thanks for these models.

ggmlStableVicunaWorks.PNG

Yeah I went back to using the old fork of GPTQ-for-LLaMA to avoid these errors until such time as text-gen-ui supports AutoGPTQ, which hopefully will be soonish.

Sign up or log in to comment