commit 3a44e42edec21a6bbbab90a5f1c1fd9a413ecf7c Author: ModelHub XC Date: Tue Jul 21 01:46:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: ggml-org/Qwen3-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..faf78e1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,51 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +Qwen3-0.6B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text + +*.gguf* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Qwen3-0.6B-BF16.gguf b/Qwen3-0.6B-BF16.gguf new file mode 100644 index 0000000..a79b0b2 --- /dev/null +++ b/Qwen3-0.6B-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a16246f5814dc0587acadcf0328186b17febf6dcaeb1b13efa9243b551d38e +size 1509347552 diff --git a/Qwen3-0.6B-Q4_0.gguf b/Qwen3-0.6B-Q4_0.gguf new file mode 100644 index 0000000..a93a919 --- /dev/null +++ b/Qwen3-0.6B-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da2572f16c06133561ce56accaa822216f2391ef4d37fba427801cd6736417d4 +size 428970080 diff --git a/Qwen3-0.6B-Q8_0.gguf b/Qwen3-0.6B-Q8_0.gguf new file mode 100644 index 0000000..af3a37a --- /dev/null +++ b/Qwen3-0.6B-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361cc68159042c36ebff7715dc5a2e4612153e88f3e9c9c234820849d6dc9e1d +size 804753632 diff --git a/Qwen3-0.6B-f16.gguf b/Qwen3-0.6B-f16.gguf new file mode 100644 index 0000000..b79ecf8 --- /dev/null +++ b/Qwen3-0.6B-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab9004daf660cd6a6ba1c07556e74fcceb2b756063ccce3f9c69d3a637b361cc +size 1509347424 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3612070 --- /dev/null +++ b/README.md @@ -0,0 +1,27 @@ +--- +license: apache-2.0 +pipeline_tag: text-generation +tags: +- gguf +- quantized +base_model: +- Qwen/Qwen3-0.6B +--- + +# Qwen3-0.6B + +Run with https://llama.app + +```bash +llama serve -hf ggml-org/Qwen3-0.6B-GGUF +``` + +### Source models +- https://huggingface.co/Qwen/Qwen3-0.6B + +### TODOs + +- add info + +> [!IMPORTANT] +> This model is automatically converted using https://github.com/ggml-org/convert diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file diff --git a/convert.log b/convert.log new file mode 100644 index 0000000..cc52c06 --- /dev/null +++ b/convert.log @@ -0,0 +1,799 @@ ++ OUTPUT_DIR=./upload-Qwen3_0.6B ++ LLAMA_CPP=./llama.cpp ++ DISPLAY_NAME=Qwen3-0.6B ++ QUANTIZE=./llama.cpp/build/bin/llama-quantize ++ python3 ./llama.cpp/convert_hf_to_gguf.py ./model-temp-Qwen3_0.6B-PRIMARY --outfile ./upload-Qwen3_0.6B/Qwen3-0.6B-BF16.gguf --outtype bf16 --model-name Qwen3-0.6B +INFO:hf-to-gguf:Loading model: model-temp-Qwen3_0.6B-PRIMARY +INFO:hf-to-gguf:Model architecture: Qwen3ForCausalLM +INFO:hf-to-gguf:gguf: indexing model part 'model.safetensors' +INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only +INFO:hf-to-gguf:Exporting model... +INFO:hf-to-gguf:output.weight, torch.bfloat16 --> BF16, shape = {1024, 151936} +INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {1024, 151936} +INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.0.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.0.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.0.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.0.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.0.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.1.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.1.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.1.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.1.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.1.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.10.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.10.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.10.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.10.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.10.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.10.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.11.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.11.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.12.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.12.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.12.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.12.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.12.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.12.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.13.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.13.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.13.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.13.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.13.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.13.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.14.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.14.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.14.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.14.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.14.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.14.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.15.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.15.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.16.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.16.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.16.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.16.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.16.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.16.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.17.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.17.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.17.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.17.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.17.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.17.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.18.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.18.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.18.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.18.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.18.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.18.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.19.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.19.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.2.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.2.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.2.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.2.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.2.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.20.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.20.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.20.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.20.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.20.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.20.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.21.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.21.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.21.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.21.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.21.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.21.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.22.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.22.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.22.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.22.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.22.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.22.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.23.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.23.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.24.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.24.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.24.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.24.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.24.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.24.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.24.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.24.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.24.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.24.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.25.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.25.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.25.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.25.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.25.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.25.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.25.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.25.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.25.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.25.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.26.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.26.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.26.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.26.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.26.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.26.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.26.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.26.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.26.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.26.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.27.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.27.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.27.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.27.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.27.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.27.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.27.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.27.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.27.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.27.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.3.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.3.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.4.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.4.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.4.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.4.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.4.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.5.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.5.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.5.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.5.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.5.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.6.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.6.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.6.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.6.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.6.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.7.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.7.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.8.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.8.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.8.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.8.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.8.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.8.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.bfloat16 --> BF16, shape = {3072, 1024} +INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.bfloat16 --> BF16, shape = {1024, 3072} +INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:blk.9.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.9.attn_k.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:blk.9.attn_output.weight, torch.bfloat16 --> BF16, shape = {2048, 1024} +INFO:hf-to-gguf:blk.9.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {128} +INFO:hf-to-gguf:blk.9.attn_q.weight, torch.bfloat16 --> BF16, shape = {1024, 2048} +INFO:hf-to-gguf:blk.9.attn_v.weight, torch.bfloat16 --> BF16, shape = {1024, 1024} +INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {1024} +INFO:hf-to-gguf:Set meta model +INFO:hf-to-gguf:Set model parameters +INFO:hf-to-gguf:gguf: context length = 40960 +INFO:hf-to-gguf:gguf: embedding length = 1024 +INFO:hf-to-gguf:gguf: feed forward length = 3072 +INFO:hf-to-gguf:gguf: head count = 16 +INFO:hf-to-gguf:gguf: key-value head count = 8 +WARNING:hf-to-gguf:Unknown RoPE type: default +INFO:hf-to-gguf:gguf: rope scaling type = NONE +INFO:hf-to-gguf:gguf: rope theta = 1000000 +INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06 +INFO:hf-to-gguf:gguf: file type = 32 +INFO:hf-to-gguf:Set model quantization version +INFO:hf-to-gguf:Set model tokenizer +INFO:gguf.vocab:Adding 151387 merge(s). +INFO:gguf.vocab:Setting special token type eos to 151645 +INFO:gguf.vocab:Setting special token type pad to 151643 +INFO:gguf.vocab:Setting special token type bos to 151643 +INFO:gguf.vocab:Setting add_bos_token to False +INFO:gguf.vocab:Setting chat_template to {%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {{- messages[0].content + '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} +{%- for message in messages[::-1] %} + {%- set index = (messages|length - 1) - loop.index0 %} + {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('') and message.content.endswith('')) %} + {%- set ns.multi_step_tool = false %} + {%- set ns.last_query_index = index %} + {%- endif %} +{%- endfor %} +{%- for message in messages %} + {%- if message.content is string %} + {%- set content = message.content %} + {%- else %} + {%- set content = '' %} + {%- endif %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} + {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {%- set reasoning_content = '' %} + {%- if message.reasoning_content is string %} + {%- set reasoning_content = message.reasoning_content %} + {%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} + {%- endif %} + {%- if loop.index0 > ns.last_query_index %} + {%- if loop.last or (not loop.last and reasoning_content) %} + {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content.strip('\n') + '\n\n\n' + content.lstrip('\n') }} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + content }} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} + {%- if enable_thinking is defined and enable_thinking is false %} + {{- '\n\n\n\n' }} + {%- endif %} +{%- endif %} +INFO:gguf.gguf_writer:Writing the following files: +INFO:gguf.gguf_writer:upload-Qwen3_0.6B/Qwen3-0.6B-BF16.gguf: n_tensors = 311, total_size = 1.5G + + Writing: 0%| | 0.00/1.50G [00:00... +llama_model_loader: - type f32: 113 tensors +llama_model_loader: - type bf16: 198 tensors +[ 1/ 311] output.weight - [ 1024, 151936, 1, 1], type = bf16, converting to q8_0 .. size = 296.75 MiB -> 157.65 MiB +[ 2/ 311] output_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 3/ 311] token_embd.weight - [ 1024, 151936, 1, 1], type = bf16, converting to q8_0 .. size = 296.75 MiB -> 157.65 MiB +[ 4/ 311] blk.0.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 5/ 311] blk.0.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 6/ 311] blk.0.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 7/ 311] blk.0.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 8/ 311] blk.0.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 9/ 311] blk.0.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 10/ 311] blk.0.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 11/ 311] blk.0.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 12/ 311] blk.0.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 13/ 311] blk.0.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 14/ 311] blk.0.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 15/ 311] blk.1.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 16/ 311] blk.1.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 17/ 311] blk.1.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 18/ 311] blk.1.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 19/ 311] blk.1.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 20/ 311] blk.1.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 21/ 311] blk.1.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 22/ 311] blk.1.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 23/ 311] blk.1.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 24/ 311] blk.1.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 25/ 311] blk.1.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 26/ 311] blk.2.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 27/ 311] blk.2.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 28/ 311] blk.2.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 29/ 311] blk.2.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 30/ 311] blk.2.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 31/ 311] blk.2.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 32/ 311] blk.2.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 33/ 311] blk.2.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 34/ 311] blk.2.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 35/ 311] blk.2.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 36/ 311] blk.2.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 37/ 311] blk.3.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 38/ 311] blk.3.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 39/ 311] blk.3.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 40/ 311] blk.3.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 41/ 311] blk.3.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 42/ 311] blk.3.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 43/ 311] blk.3.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 44/ 311] blk.3.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 45/ 311] blk.3.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 46/ 311] blk.3.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 47/ 311] blk.3.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 48/ 311] blk.4.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 49/ 311] blk.4.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 50/ 311] blk.4.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 51/ 311] blk.4.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 52/ 311] blk.4.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 53/ 311] blk.4.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 54/ 311] blk.4.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 55/ 311] blk.4.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 56/ 311] blk.4.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 57/ 311] blk.4.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 58/ 311] blk.4.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 59/ 311] blk.5.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 60/ 311] blk.5.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 61/ 311] blk.5.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 62/ 311] blk.5.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 63/ 311] blk.5.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 64/ 311] blk.5.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 65/ 311] blk.5.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 66/ 311] blk.5.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 67/ 311] blk.5.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 68/ 311] blk.5.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 69/ 311] blk.5.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 70/ 311] blk.6.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 71/ 311] blk.6.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 72/ 311] blk.6.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 73/ 311] blk.6.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 74/ 311] blk.6.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 75/ 311] blk.6.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 76/ 311] blk.6.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 77/ 311] blk.6.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 78/ 311] blk.6.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 79/ 311] blk.6.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 80/ 311] blk.6.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 81/ 311] blk.7.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 82/ 311] blk.7.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 83/ 311] blk.7.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 84/ 311] blk.7.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 85/ 311] blk.7.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 86/ 311] blk.7.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 87/ 311] blk.7.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 88/ 311] blk.7.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 89/ 311] blk.7.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 90/ 311] blk.7.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 91/ 311] blk.7.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 92/ 311] blk.8.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 93/ 311] blk.8.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 94/ 311] blk.8.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 95/ 311] blk.8.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 96/ 311] blk.8.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 97/ 311] blk.8.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 98/ 311] blk.8.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 99/ 311] blk.8.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 100/ 311] blk.8.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 101/ 311] blk.8.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 102/ 311] blk.8.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 103/ 311] blk.9.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 104/ 311] blk.9.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 105/ 311] blk.9.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 106/ 311] blk.9.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 107/ 311] blk.9.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 108/ 311] blk.9.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 109/ 311] blk.9.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 110/ 311] blk.9.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 111/ 311] blk.9.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 112/ 311] blk.9.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 113/ 311] blk.9.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 114/ 311] blk.10.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 115/ 311] blk.10.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 116/ 311] blk.10.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 117/ 311] blk.10.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 118/ 311] blk.10.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 119/ 311] blk.10.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 120/ 311] blk.10.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 121/ 311] blk.10.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 122/ 311] blk.10.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 123/ 311] blk.10.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 124/ 311] blk.10.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 125/ 311] blk.11.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 126/ 311] blk.11.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 127/ 311] blk.11.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 128/ 311] blk.11.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 129/ 311] blk.11.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 130/ 311] blk.11.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 131/ 311] blk.11.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 132/ 311] blk.11.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 133/ 311] blk.11.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 134/ 311] blk.11.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 135/ 311] blk.11.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 136/ 311] blk.12.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 137/ 311] blk.12.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 138/ 311] blk.12.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 139/ 311] blk.12.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 140/ 311] blk.12.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 141/ 311] blk.12.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 142/ 311] blk.12.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 143/ 311] blk.12.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 144/ 311] blk.12.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 145/ 311] blk.12.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 146/ 311] blk.12.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 147/ 311] blk.13.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 148/ 311] blk.13.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 149/ 311] blk.13.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 150/ 311] blk.13.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 151/ 311] blk.13.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 152/ 311] blk.13.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 153/ 311] blk.13.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 154/ 311] blk.13.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 155/ 311] blk.13.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 156/ 311] blk.13.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 157/ 311] blk.13.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 158/ 311] blk.14.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 159/ 311] blk.14.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 160/ 311] blk.14.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 161/ 311] blk.14.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 162/ 311] blk.14.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 163/ 311] blk.14.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 164/ 311] blk.14.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 165/ 311] blk.14.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 166/ 311] blk.14.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 167/ 311] blk.14.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 168/ 311] blk.14.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 169/ 311] blk.15.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 170/ 311] blk.15.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 171/ 311] blk.15.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 172/ 311] blk.15.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 173/ 311] blk.15.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 174/ 311] blk.15.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 175/ 311] blk.15.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 176/ 311] blk.15.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 177/ 311] blk.15.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 178/ 311] blk.15.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 179/ 311] blk.15.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 180/ 311] blk.16.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 181/ 311] blk.16.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 182/ 311] blk.16.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 183/ 311] blk.16.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 184/ 311] blk.16.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 185/ 311] blk.16.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 186/ 311] blk.16.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 187/ 311] blk.16.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 188/ 311] blk.16.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 189/ 311] blk.16.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 190/ 311] blk.16.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 191/ 311] blk.17.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 192/ 311] blk.17.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 193/ 311] blk.17.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 194/ 311] blk.17.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 195/ 311] blk.17.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 196/ 311] blk.17.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 197/ 311] blk.17.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 198/ 311] blk.17.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 199/ 311] blk.17.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 200/ 311] blk.17.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 201/ 311] blk.17.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 202/ 311] blk.18.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 203/ 311] blk.18.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 204/ 311] blk.18.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 205/ 311] blk.18.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 206/ 311] blk.18.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 207/ 311] blk.18.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 208/ 311] blk.18.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 209/ 311] blk.18.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 210/ 311] blk.18.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 211/ 311] blk.18.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 212/ 311] blk.18.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 213/ 311] blk.19.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 214/ 311] blk.19.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 215/ 311] blk.19.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 216/ 311] blk.19.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 217/ 311] blk.19.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 218/ 311] blk.19.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 219/ 311] blk.19.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 220/ 311] blk.19.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 221/ 311] blk.19.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 222/ 311] blk.19.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 223/ 311] blk.19.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 224/ 311] blk.20.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 225/ 311] blk.20.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 226/ 311] blk.20.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 227/ 311] blk.20.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 228/ 311] blk.20.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 229/ 311] blk.20.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 230/ 311] blk.20.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 231/ 311] blk.20.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 232/ 311] blk.20.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 233/ 311] blk.20.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 234/ 311] blk.20.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 235/ 311] blk.21.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 236/ 311] blk.21.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 237/ 311] blk.21.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 238/ 311] blk.21.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 239/ 311] blk.21.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 240/ 311] blk.21.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 241/ 311] blk.21.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 242/ 311] blk.21.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 243/ 311] blk.21.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 244/ 311] blk.21.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 245/ 311] blk.21.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 246/ 311] blk.22.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 247/ 311] blk.22.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 248/ 311] blk.22.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 249/ 311] blk.22.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 250/ 311] blk.22.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 251/ 311] blk.22.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 252/ 311] blk.22.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 253/ 311] blk.22.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 254/ 311] blk.22.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 255/ 311] blk.22.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 256/ 311] blk.22.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 257/ 311] blk.23.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 258/ 311] blk.23.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 259/ 311] blk.23.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 260/ 311] blk.23.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 261/ 311] blk.23.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 262/ 311] blk.23.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 263/ 311] blk.23.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 264/ 311] blk.23.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 265/ 311] blk.23.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 266/ 311] blk.23.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 267/ 311] blk.23.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 268/ 311] blk.24.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 269/ 311] blk.24.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 270/ 311] blk.24.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 271/ 311] blk.24.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 272/ 311] blk.24.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 273/ 311] blk.24.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 274/ 311] blk.24.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 275/ 311] blk.24.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 276/ 311] blk.24.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 277/ 311] blk.24.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 278/ 311] blk.24.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 279/ 311] blk.25.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 280/ 311] blk.25.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 281/ 311] blk.25.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 282/ 311] blk.25.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 283/ 311] blk.25.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 284/ 311] blk.25.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 285/ 311] blk.25.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 286/ 311] blk.25.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 287/ 311] blk.25.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 288/ 311] blk.25.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 289/ 311] blk.25.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 290/ 311] blk.26.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 291/ 311] blk.26.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 292/ 311] blk.26.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 293/ 311] blk.26.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 294/ 311] blk.26.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 295/ 311] blk.26.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 296/ 311] blk.26.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 297/ 311] blk.26.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 298/ 311] blk.26.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 299/ 311] blk.26.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 300/ 311] blk.26.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 301/ 311] blk.27.attn_k.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 302/ 311] blk.27.attn_k_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 303/ 311] blk.27.attn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 304/ 311] blk.27.attn_output.weight - [ 2048, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 305/ 311] blk.27.attn_q.weight - [ 1024, 2048, 1, 1], type = bf16, converting to q8_0 .. size = 4.00 MiB -> 2.12 MiB +[ 306/ 311] blk.27.attn_q_norm.weight - [ 128, 1, 1, 1], type = f32, size = 0.000 MiB +[ 307/ 311] blk.27.attn_v.weight - [ 1024, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 2.00 MiB -> 1.06 MiB +[ 308/ 311] blk.27.ffn_down.weight - [ 3072, 1024, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 309/ 311] blk.27.ffn_gate.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +[ 310/ 311] blk.27.ffn_norm.weight - [ 1024, 1, 1, 1], type = f32, size = 0.004 MiB +[ 311/ 311] blk.27.ffn_up.weight - [ 1024, 3072, 1, 1], type = bf16, converting to q8_0 .. size = 6.00 MiB -> 3.19 MiB +llama_model_quantize_impl: model size = 1433.75 MiB (16.00 BPW) +llama_model_quantize_impl: quant size = 761.80 MiB (8.50 BPW) + +llama_quantize: quantize time = 3300.43 ms +llama_quantize: total time = 3300.43 ms ++ echo Qwen3-0.6B-BF16.gguf ++ echo Qwen3-0.6B-Q8_0.gguf