From be55d600cc23364a81653db8351e3a0ff4cd2515 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 11 May 2026 02:00:21 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: maple77/GGUF-ALL Source: Original Platform --- .gitattributes | 37 +++ Qwen2/Qwen2-0.5B-Instruct.gguf | 3 + Qwen2/Qwen2-0.5B.gguf | 3 + Qwen2/Qwen2-1.5B-Instruct.gguf | 3 + Qwen2/Qwen2-1.5B.gguf | 3 + Qwen2/Qwen2-7B-Instruct-fp16.gguf | 3 + Qwen2/Qwen2-7B-Instruct-q5_0.gguf | 3 + Qwen2/Qwen2-7B-Instruct-q5_k_m.gguf | 3 + Qwen2/Qwen2-7B-Instruct-q6_k.gguf | 3 + Qwen2/Qwen2-7B-Instruct-q8_0.gguf | 3 + Qwen2/Qwen2-7B.gguf | 3 + README.md | 374 ++++++++++++++++++++++++++++ configuration.json | 1 + 13 files changed, 442 insertions(+) create mode 100644 .gitattributes create mode 100644 Qwen2/Qwen2-0.5B-Instruct.gguf create mode 100644 Qwen2/Qwen2-0.5B.gguf create mode 100644 Qwen2/Qwen2-1.5B-Instruct.gguf create mode 100644 Qwen2/Qwen2-1.5B.gguf create mode 100644 Qwen2/Qwen2-7B-Instruct-fp16.gguf create mode 100644 Qwen2/Qwen2-7B-Instruct-q5_0.gguf create mode 100644 Qwen2/Qwen2-7B-Instruct-q5_k_m.gguf create mode 100644 Qwen2/Qwen2-7B-Instruct-q6_k.gguf create mode 100644 Qwen2/Qwen2-7B-Instruct-q8_0.gguf create mode 100644 Qwen2/Qwen2-7B.gguf create mode 100644 README.md create mode 100644 configuration.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b7e9e3a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2/Qwen2-0.5B-Instruct.gguf b/Qwen2/Qwen2-0.5B-Instruct.gguf new file mode 100644 index 0000000..ecfb27b --- /dev/null +++ b/Qwen2/Qwen2-0.5B-Instruct.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07de5ee9a80150a00b07de2b47003a2312296338296ad3d24766effbafdb4b9 +size 994153888 diff --git a/Qwen2/Qwen2-0.5B.gguf b/Qwen2/Qwen2-0.5B.gguf new file mode 100644 index 0000000..1903988 --- /dev/null +++ b/Qwen2/Qwen2-0.5B.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f33f03601f7f0939c14d12700637b6683209a7f9dd6226e6359fd085940606b +size 994153888 diff --git a/Qwen2/Qwen2-1.5B-Instruct.gguf b/Qwen2/Qwen2-1.5B-Instruct.gguf new file mode 100644 index 0000000..a2fb0f2 --- /dev/null +++ b/Qwen2/Qwen2-1.5B-Instruct.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a79e0e0407877562e18e681c07ba5742ca5010a59e8dd067f2db7ea1aec406f +size 3093666400 diff --git a/Qwen2/Qwen2-1.5B.gguf b/Qwen2/Qwen2-1.5B.gguf new file mode 100644 index 0000000..ed1fd05 --- /dev/null +++ b/Qwen2/Qwen2-1.5B.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e7929718678c2b594dab7fbec7470bc311fabb57787f0f5310381629bfbf02 +size 3093666400 diff --git a/Qwen2/Qwen2-7B-Instruct-fp16.gguf b/Qwen2/Qwen2-7B-Instruct-fp16.gguf new file mode 100644 index 0000000..0f48b86 --- /dev/null +++ b/Qwen2/Qwen2-7B-Instruct-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df8256ba7781d491a0b3be8790e69dbcc8fd6c8279f10e1b6478ab0995c0e20 +size 15237850656 diff --git a/Qwen2/Qwen2-7B-Instruct-q5_0.gguf b/Qwen2/Qwen2-7B-Instruct-q5_0.gguf new file mode 100644 index 0000000..15d1b28 --- /dev/null +++ b/Qwen2/Qwen2-7B-Instruct-q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7f0cd83cab30e3d817f285acb5002cb7889281d0fb83d7212b201b22e8e160c +size 5315173920 diff --git a/Qwen2/Qwen2-7B-Instruct-q5_k_m.gguf b/Qwen2/Qwen2-7B-Instruct-q5_k_m.gguf new file mode 100644 index 0000000..5fe2aa3 --- /dev/null +++ b/Qwen2/Qwen2-7B-Instruct-q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258dd2fa1bdf98b85327774e1fd36e2268c2a4b68eb9021d71106449ee4ba9d5 +size 5444828704 diff --git a/Qwen2/Qwen2-7B-Instruct-q6_k.gguf b/Qwen2/Qwen2-7B-Instruct-q6_k.gguf new file mode 100644 index 0000000..ab22429 --- /dev/null +++ b/Qwen2/Qwen2-7B-Instruct-q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f3ecf4453db5de781ee64e7c4022d79ded6ce84de00621faa02541ff19c3b1 +size 6254196256 diff --git a/Qwen2/Qwen2-7B-Instruct-q8_0.gguf b/Qwen2/Qwen2-7B-Instruct-q8_0.gguf new file mode 100644 index 0000000..fef98b5 --- /dev/null +++ b/Qwen2/Qwen2-7B-Instruct-q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55b1c74b48d4fdf9868f0f7ee06fd2aae4d3a2baf0be474a006e1aa4ab98ab81 +size 8098522656 diff --git a/Qwen2/Qwen2-7B.gguf b/Qwen2/Qwen2-7B.gguf new file mode 100644 index 0000000..6faeab5 --- /dev/null +++ b/Qwen2/Qwen2-7B.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b0984604c20d8084b04d1301897f6672ed6db4fcf43eeda7bec568fec73a277 +size 15237850624 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d5ebb3f --- /dev/null +++ b/README.md @@ -0,0 +1,374 @@ +通过llama.cpp转换的gguf，未量化，测试效果感觉并不咋地 + +``` +$ python llama.cpp/convert-hf-to-gguf.py models/huggingface/llm/Qwen/Qwen2-1.5B-Instruct --outfile models/GGUF-ALL/Qwen2-1.5B-Instruct.gguf +^[[AINFO:hf-to-gguf:Loading model: Qwen2-1.5B-Instruct +INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only +INFO:hf-to-gguf:Set model parameters +INFO:hf-to-gguf:gguf: context length = 32768 +INFO:hf-to-gguf:gguf: embedding length = 1536 +INFO:hf-to-gguf:gguf: feed forward length = 8960 +INFO:hf-to-gguf:gguf: head count = 12 +INFO:hf-to-gguf:gguf: key-value head count = 2 +INFO:hf-to-gguf:gguf: rope theta = 1000000.0 +INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06 +INFO:hf-to-gguf:gguf: file type = 1 +INFO:hf-to-gguf:Set model tokenizer +Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained. +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 chat_template to {% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system +You are a helpful assistant.<|im_end|> +' }}{% endif %}{{'<|im_start|>' + message['role'] + ' +' + message['content'] + '<|im_end|>' + ' +'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant +' }}{% endif %} +INFO:hf-to-gguf:Exporting model to 'models/GGUF-ALL/Qwen2-1.5B-Instruct.gguf' +INFO:hf-to-gguf:gguf: loading model part 'model.safetensors' +INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> F16, shape = {1536, 151936} +INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.0.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.0.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.0.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.0.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.0.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.0.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.0.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.1.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.1.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.1.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.1.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.1.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.1.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.1.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.10.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.10.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.10.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.10.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.10.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.10.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.10.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.11.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.11.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.11.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.12.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.12.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.12.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.12.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.12.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.12.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.12.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.13.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.13.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.13.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.13.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.13.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.13.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.13.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.14.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.14.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.14.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.14.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.14.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.14.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.14.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.15.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.15.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.15.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.16.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.16.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.16.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.16.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.16.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.16.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.16.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.16.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.16.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.16.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.16.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.17.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.17.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.17.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.17.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.17.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.17.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.17.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.17.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.17.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.17.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.17.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.18.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.18.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.18.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.18.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.18.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.18.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.18.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.18.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.18.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.18.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.18.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.19.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.19.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.19.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.19.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.19.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.19.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.19.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.2.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.2.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.2.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.2.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.2.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.2.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.2.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.20.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.20.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.20.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.20.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.20.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.20.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.20.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.20.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.20.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.20.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.20.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.21.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.21.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.21.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.21.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.21.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.21.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.21.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.21.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.21.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.21.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.21.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.22.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.22.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.22.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.22.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.22.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.22.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.22.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.22.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.22.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.22.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.22.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.23.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.23.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.23.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.23.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.23.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.23.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.23.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.24.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.24.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.24.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.24.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.24.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.24.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.24.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.24.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.24.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.24.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.24.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.25.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.25.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.25.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.25.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.25.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.25.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.25.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.25.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.25.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.25.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.25.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.26.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.26.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.26.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.26.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.26.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.26.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.26.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.26.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.26.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.26.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.26.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.27.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.27.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.27.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.27.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.27.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.27.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.27.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.27.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.27.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.27.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.27.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.3.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.3.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.3.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.4.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.4.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.4.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.4.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.4.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.4.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.4.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.5.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.5.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.5.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.5.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.5.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.5.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.5.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.6.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.6.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.6.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.6.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.6.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.6.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.6.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.7.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.7.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.7.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.8.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.8.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.8.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.8.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.8.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.8.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.8.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.bfloat16 --> F16, shape = {8960, 1536} +INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.bfloat16 --> F16, shape = {1536, 8960} +INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.9.attn_k.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.9.attn_k.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:blk.9.attn_output.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.9.attn_q.bias, torch.bfloat16 --> F32, shape = {1536} +INFO:hf-to-gguf:blk.9.attn_q.weight, torch.bfloat16 --> F16, shape = {1536, 1536} +INFO:hf-to-gguf:blk.9.attn_v.bias, torch.bfloat16 --> F32, shape = {256} +INFO:hf-to-gguf:blk.9.attn_v.weight, torch.bfloat16 --> F16, shape = {1536, 256} +INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {1536} +huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... +To disable this warning, you can either: + - Avoid using `tokenizers` before the fork if possible + - Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) +Writing: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3.09G/3.09G [00:05<00:00, 555Mbyte/s] +INFO:hf-to-gguf:Model successfully exported to 'models/GGUF-ALL/Qwen2-1.5B-Instruct.gguf' +``` \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..9fbcf95 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"task":"text-generation"} \ No newline at end of file