diff --git "a/Llama3.2_1B-SQL.ipynb" "b/Llama3.2_1B-SQL.ipynb" deleted file mode 100644--- "a/Llama3.2_1B-SQL.ipynb" +++ /dev/null @@ -1,2387 +0,0 @@ -{ - "cells": [ - { - "cell_type": "code", - "execution_count": 6, - "metadata": { - "id": "2eSvM9zX_2d3" - }, - "outputs": [], - "source": [ - "%%capture\n", - "!pip install unsloth vllm" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "metadata": { - "colab": { - "base_uri": "https://localhost:8080/" - }, - "id": "QmUBVEnvCDJv", - "outputId": "3dfcd57d-baf9-42bb-fd36-3f9d123e5539" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "🦥 Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", - "🦥 Unsloth Zoo will now patch everything to make training faster!\n", - "INFO 07-07 15:54:12 [importing.py:53] Triton module has been replaced with a placeholder.\n", - "INFO 07-07 15:54:12 [__init__.py:239] Automatically detected platform cuda.\n", - "==((====))== Unsloth 2025.6.12: Fast Llama patching. Transformers: 4.53.0. vLLM: 0.8.5.post1.\n", - " \\\\ /| Tesla T4. Num GPUs = 1. Max memory: 14.741 GB. Platform: Linux.\n", - "O^O/ \\_/ \\ Torch: 2.6.0+cu124. CUDA: 7.5. CUDA Toolkit: 12.4. Triton: 3.2.0\n", - "\\ / Bfloat16 = FALSE. FA [Xformers = 0.0.29.post2. FA2 = False]\n", - " \"-____-\" Free license: http://github.com/unslothai/unsloth\n", - "Unsloth: Fast downloading is enabled - ignore downloading bars which are red colored!\n" - ] - } - ], - "source": [ - "from unsloth import FastLanguageModel\n", - "import torch\n", - "max_seq_length = 2048\n", - "load_in_4bit = True\n", - "dtype = None\n", - "\n", - "model, tokenizer = FastLanguageModel.from_pretrained(\n", - " model_name = \"unsloth/Llama-3.2-1B-Instruct\",\n", - " max_seq_length = max_seq_length,\n", - " dtype = dtype,\n", - " load_in_4bit = load_in_4bit,\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "metadata": { - "id": "6bZsfBuZDeCL", - "colab": { - "base_uri": "https://localhost:8080/" - }, - "outputId": "21961fc5-9c9e-4467-da42-55f1fb4db525" - }, - "outputs": [ - { - "output_type": "stream", - "name": "stderr", - "text": [ - "Unsloth 2025.6.12 patched 16 layers with 16 QKV layers, 16 O layers and 16 MLP layers.\n" - ] - } - ], - "source": [ - "model = FastLanguageModel.get_peft_model(\n", - " model,\n", - " r = 16,\n", - " target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n", - " \"gate_proj\", \"up_proj\", \"down_proj\",],\n", - " lora_alpha = 16,\n", - " lora_dropout = 0,\n", - " bias = \"none\",\n", - " use_gradient_checkpointing = \"unsloth\",\n", - " random_state = 3407,\n", - " use_rslora = False,\n", - " loftq_config = None,\n", - ")" - ] - }, - { - "cell_type": "code", - "execution_count": 9, - "metadata": { - "id": "LjY75GoYUCB8" - }, - "outputs": [], - "source": [ - "from unsloth.chat_templates import get_chat_template\n", - "\n", - "tokenizer = get_chat_template(\n", - " tokenizer,\n", - " chat_template = \"llama-3.1\",\n", - ")\n", - "\n", - "def formatting_prompts_func(examples):\n", - " convos = examples[\"conversations\"]\n", - " texts = [tokenizer.apply_chat_template(convo, tokenize = False, add_generation_prompt = False) for convo in convos]\n", - " return { \"text\" : texts, }\n", - "pass\n", - "\n", - "from datasets import load_dataset\n", - "dataset = load_dataset(\"mlabonne/synthetic_text_to_sql-ShareGPT\", split = \"train\")" - ] - }, - { - "cell_type": "code", - "source": [ - "from unsloth.chat_templates import standardize_sharegpt\n", - "dataset = standardize_sharegpt(dataset)\n", - "dataset = dataset.map(formatting_prompts_func, batched = True,)" - ], - "metadata": { - "id": "oPXzJZzHEgXe", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 49, - "referenced_widgets": [ - "974c4eb606864332b3e99b158e5c2248", - "fb0a8933009d47db891f46fe7b5004e5", - "cb02d10b76254e73b3c49f2f11b57269", - "b4d1e9f1cb0f46babe6ce0e026d8565a", - "8000159229ca4b1785ecb4683a282e49", - "35efbf67792d4a7f9a253d633451563a", - "ba859ed12a6245d2bf839087217cabe3", - "00b8f1da5e5e4f15a562fb07a6259481", - "cc5f0f02fff2499e977b505037a3d6f6", - "6f15880e16514ab5844763b1d45a85f7", - "889be39cf43042549042e31fdc438e7f" - ] - }, - "outputId": "26d8c8e3-c507-43fc-e185-3b7acb540d5c" - }, - "execution_count": 10, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "Map: 0%| | 0/105851 [00:00<|start_header_id|>system<|end_header_id|>\\n\\nCutting Knowledge Date: December 2023\\nToday Date: 26 July 2024\\n\\n<|eot_id|><|start_header_id|>user<|end_header_id|>\\n\\nCREATE TABLE Beds (State VARCHAR(50), Beds INT); INSERT INTO Beds (State, Beds) VALUES ('California', 100000), ('Texas', 85000), ('New York', 70000);\\n\\nWhat is the total number of hospital beds in each state?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\nSELECT State, SUM(Beds) FROM Beds GROUP BY State;\\n\\nThis query calculates the total number of hospital beds in each state in the Beds table. It does this by using the SUM function on the Beds column and grouping the results by the State column.<|eot_id|>\"" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "string" - } - }, - "metadata": {}, - "execution_count": 12 - } - ] - }, - { - "cell_type": "code", - "execution_count": 13, - "metadata": { - "id": "95_Nn-89DhsL", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 49, - "referenced_widgets": [ - "73464bc430fa471c9da348275de32220", - "42362451ce674deab324dd571e2e63a8", - "9dfde51c9a794aa7bb96e260aae71756", - "37837a2b2aae45369edab2d9b84e2f40", - "110a65ffc5e54f799f98dcace707e3c3", - "b3a4f1e5e2b349f0bc9af660047c5947", - "b68154275bad4c81aa427f4981b5fb1b", - "73930cb531bb4e0286b9530fa1e26be2", - "9eba57bbcec94d9c871704856fb7e1d1", - "11097e54c5314914a0a65c0b0ec1bcbb", - "462bf508424840309de35c510cd41be6" - ] - }, - "outputId": "e2a713ee-ec7b-43cf-8126-43f42ad3903c" - }, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "Unsloth: Tokenizing [\"text\"]: 0%| | 0/105851 [00:00user<|end_header_id|>\\n\\n\",\n", - " response_part = \"<|start_header_id|>assistant<|end_header_id|>\\n\\n\",\n", - ")" - ], - "metadata": { - "id": "juQiExuBG5Bt", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 49, - "referenced_widgets": [ - "85d3e396d5a944e1a6b7f52ada151f20", - "306968a12f004b239b12bb388c5ac60d", - "3e79f19c2d554d8c8660e77b6a670e07", - "3c6ffaff3ed4427086ad3faabee5eb2a", - "20bc91381af149c3a4db7953bac757a9", - "9032fc0aae5048338f3cf7c5128f286a", - "045df3567d80438486b553c17281e955", - "ceee3c9296a545e0a3fc4a37c78b473a", - "5ba9d0d0cc564eb29832e6ee2ad57eda", - "b1d1541ca63f4b4383e8b0644d8a7b9f", - "74c5c9c611b8457a946e9e92e22dc560" - ] - }, - "outputId": "a695236a-a5e8-4fdd-bbd1-db4f2819dc5f" - }, - "execution_count": 14, - "outputs": [ - { - "output_type": "display_data", - "data": { - "text/plain": [ - "Map (num_proc=2): 0%| | 0/105851 [00:00" - ], - "text/html": [ - "\n", - "
\n", - " \n", - " \n", - " [60/60 00:57, Epoch 0/1]\n", - "
\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
StepTraining Loss
10.787000
21.163600
30.800200
40.840700
50.729900
60.736900
70.719700
80.825100
90.823900
100.527000
110.633000
120.600000
130.843800
140.502000
150.451900
160.783100
170.524600
180.547500
190.567600
200.664800
210.626300
220.721100
230.658500
240.273600
250.583500
260.598700
270.736900
280.682900
290.900400
300.427400
310.561300
320.652900
330.609300
340.527000
350.611300
360.700100
370.638500
380.678900
390.636300
400.671000
410.470600
420.492100
430.515200
440.647000
450.587000
460.530000
470.461400
480.612100
490.460100
500.501100
510.747500
520.588500
530.580900
540.566300
550.496700
560.676100
570.503200
580.419500
590.661100
600.621400

" - ] - }, - "metadata": {} - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Unsloth: Will smartly offload gradients to save VRAM!\n" - ] - } - ], - "source": [ - "trainer_stats = trainer.train()" - ] - }, - { - "cell_type": "code", - "execution_count": 16, - "metadata": { - "id": "kR3gIAX-SM2q", - "outputId": "5e1ca86c-05aa-4151-803e-9d26aa90c616", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "outputs": [ - { - "output_type": "stream", - "name": "stderr", - "text": [ - "The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n", - "LlamaForCausalLM has no `_prepare_4d_causal_attention_mask_with_cache_position` method defined in its base modeling class. Compiled forward passes will be sub-optimal. If you're writing code, see Llama for an example implementation. If you're a user, please report this issue on GitHub.\n" - ] - }, - { - "output_type": "execute_result", - "data": { - "text/plain": [ - "[\"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\\n\\nCutting Knowledge Date: December 2023\\nToday Date: 26 July 2024\\n\\n<|eot_id|><|start_header_id|>user<|end_header_id|>\\n\\nCREATE TABLE Students (Name VARCHAR(50), Marks INT);\\nINSERT INTO Students (Name, Marks) VALUES \\n('Alice', 85), \\n('Bob', 90), \\n('Charlie', 78);\\n\\nHow do I find the average marks of all students?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\\n\\nSELECT AVG(Marks) AS AverageMarks FROM Students;\\n\\nThe SQL query calculates the average marks of all students by selecting the `AVG(Marks)` function on the 'Marks' column, and then calculating the average using the `AVG()` function.<|eot_id|>\"]" - ] - }, - "metadata": {}, - "execution_count": 16 - } - ], - "source": [ - "from unsloth.chat_templates import get_chat_template\n", - "\n", - "tokenizer = get_chat_template(\n", - " tokenizer,\n", - " chat_template = \"llama-3.1\",\n", - ")\n", - "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", - "\n", - "messages = [\n", - " {\n", - " \"role\": \"user\",\n", - " \"content\": \"\"\"CREATE TABLE Students (Name VARCHAR(50), Marks INT);\n", - "INSERT INTO Students (Name, Marks) VALUES\n", - "('Alice', 85),\n", - "('Bob', 90),\n", - "('Charlie', 78);\n", - "\n", - "How do I find the average marks of all students?\"\"\"\n", - " }\n", - "]\n", - "inputs = tokenizer.apply_chat_template(\n", - " messages,\n", - " tokenize = True,\n", - " add_generation_prompt = True, # Must add for generation\n", - " return_tensors = \"pt\",\n", - ").to(\"cuda\")\n", - "\n", - "outputs = model.generate(input_ids = inputs, max_new_tokens = 64, use_cache = True,\n", - " temperature = 1.5, min_p = 0.1)\n", - "tokenizer.batch_decode(outputs)" - ] - }, - { - "cell_type": "code", - "source": [ - "model.save_pretrained_gguf(\"model\",tokenizer,quantization_method = \"q4_k_m\")" - ], - "metadata": { - "id": "vLW-e6shZ7Sr", - "outputId": "7bc80b5a-2b22-4b49-ce20-3da1239a8a30", - "colab": { - "base_uri": "https://localhost:8080/" - } - }, - "execution_count": 17, - "outputs": [ - { - "output_type": "stream", - "name": "stderr", - "text": [ - "Unsloth: You have 1 CPUs. Using `safe_serialization` is 10x slower.\n", - "We shall switch to Pytorch saving, which might take 3 minutes and not 30 minutes.\n", - "To force `safe_serialization`, set it to `None` instead.\n", - "Unsloth: Kaggle/Colab has limited disk space. We need to delete the downloaded\n", - "model which will save 4-16GB of disk space, allowing you to save on Kaggle/Colab.\n", - "Unsloth: Will remove a cached repo with size 1.1G\n" - ] - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Unsloth: Merging 4bit and LoRA weights to 16bit...\n", - "Unsloth: Will use up to 5.38 out of 12.67 RAM for saving.\n", - "Unsloth: Saving model... This might take 5 minutes ...\n" - ] - }, - { - "output_type": "stream", - "name": "stderr", - "text": [ - "100%|██████████| 16/16 [00:00<00:00, 24.56it/s]\n" - ] - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Unsloth: Saving tokenizer... Done.\n", - "Unsloth: Saving model/pytorch_model.bin...\n", - "Done.\n" - ] - }, - { - "output_type": "stream", - "name": "stderr", - "text": [ - "Unsloth: Converting llama model. Can use fast conversion = False.\n" - ] - }, - { - "output_type": "stream", - "name": "stdout", - "text": [ - "==((====))== Unsloth: Conversion from QLoRA to GGUF information\n", - " \\\\ /| [0] Installing llama.cpp might take 3 minutes.\n", - "O^O/ \\_/ \\ [1] Converting HF to GGUF 16bits might take 3 minutes.\n", - "\\ / [2] Converting GGUF 16bits to ['q4_k_m'] might take 10 minutes each.\n", - " \"-____-\" In total, you will have to wait at least 16 minutes.\n", - "\n", - "Unsloth: Installing llama.cpp. This might take 3 minutes...\n", - "Unsloth: CMAKE detected. Finalizing some steps for installation.\n", - "Unsloth: [1] Converting model at model into f16 GGUF format.\n", - "The output location will be /content/model/unsloth.F16.gguf\n", - "This might take 3 minutes...\n", - "INFO:hf-to-gguf:Loading model: model\n", - "INFO:hf-to-gguf:Model architecture: LlamaForCausalLM\n", - "INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only\n", - "INFO:hf-to-gguf:Exporting model...\n", - "INFO:hf-to-gguf:rope_freqs.weight, torch.float32 --> F32, shape = {32}\n", - "INFO:hf-to-gguf:gguf: loading model part 'pytorch_model.bin'\n", - "INFO:hf-to-gguf:token_embd.weight, torch.float16 --> F16, shape = {2048, 128256}\n", - "INFO:hf-to-gguf:blk.0.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.0.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.0.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.0.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.0.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.0.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.0.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.0.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.1.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.1.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.1.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.1.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.1.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.1.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.1.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.1.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.2.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.2.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.2.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.2.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.2.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.2.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.2.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.2.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.3.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.3.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.3.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.3.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.3.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.3.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.3.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.3.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.4.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.4.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.4.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.4.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.4.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.4.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.4.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.4.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.5.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.5.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.5.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.5.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.5.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.5.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.5.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.5.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.6.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.6.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.6.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.6.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.6.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.6.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.6.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.6.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.7.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.7.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.7.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.7.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.7.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.7.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.7.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.7.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.8.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.8.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.8.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.8.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.8.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.8.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.8.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.8.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.9.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.9.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.9.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.9.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.9.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.9.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.9.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.9.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.10.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.10.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.10.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.10.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.10.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.10.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.10.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.10.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.11.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.11.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.11.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.11.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.11.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.11.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.11.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.11.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.12.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.12.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.12.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.12.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.12.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.12.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.12.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.12.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.13.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.13.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.13.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.13.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.13.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.13.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.13.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.13.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.14.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.14.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.14.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.14.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.14.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.14.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.14.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.14.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.15.attn_q.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.15.attn_k.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.15.attn_v.weight, torch.float16 --> F16, shape = {2048, 512}\n", - "INFO:hf-to-gguf:blk.15.attn_output.weight, torch.float16 --> F16, shape = {2048, 2048}\n", - "INFO:hf-to-gguf:blk.15.ffn_gate.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.15.ffn_up.weight, torch.float16 --> F16, shape = {2048, 8192}\n", - "INFO:hf-to-gguf:blk.15.ffn_down.weight, torch.float16 --> F16, shape = {8192, 2048}\n", - "INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:blk.15.ffn_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:output_norm.weight, torch.float16 --> F32, shape = {2048}\n", - "INFO:hf-to-gguf:Set meta model\n", - "INFO:hf-to-gguf:Set model parameters\n", - "INFO:hf-to-gguf:gguf: context length = 131072\n", - "INFO:hf-to-gguf:gguf: embedding length = 2048\n", - "INFO:hf-to-gguf:gguf: feed forward length = 8192\n", - "INFO:hf-to-gguf:gguf: head count = 32\n", - "INFO:hf-to-gguf:gguf: key-value head count = 8\n", - "INFO:hf-to-gguf:gguf: rope theta = 500000.0\n", - "INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-05\n", - "INFO:hf-to-gguf:gguf: file type = 1\n", - "INFO:hf-to-gguf:Set model quantization version\n", - "INFO:hf-to-gguf:Set model tokenizer\n", - "INFO:numexpr.utils:NumExpr defaulting to 2 threads.\n", - "WARNING:gguf.vocab:Unknown separator token '<|begin_of_text|>' in TemplateProcessing\n", - "INFO:gguf.vocab:Adding 280147 merge(s).\n", - "INFO:gguf.vocab:Setting special token type bos to 128000\n", - "INFO:gguf.vocab:Setting special token type eos to 128009\n", - "INFO:gguf.vocab:Setting special token type pad to 128004\n", - "INFO:gguf.vocab:Setting add_bos_token to True\n", - "INFO:gguf.vocab:Setting add_sep_token to False\n", - "INFO:gguf.vocab:Setting chat_template to {{- bos_token }}\n", - "{%- if custom_tools is defined %}\n", - " {%- set tools = custom_tools %}\n", - "{%- endif %}\n", - "{%- if not tools_in_user_message is defined %}\n", - " {%- set tools_in_user_message = true %}\n", - "{%- endif %}\n", - "{%- if not date_string is defined %}\n", - " {%- set date_string = \"26 July 2024\" %}\n", - "{%- endif %}\n", - "{%- if not tools is defined %}\n", - " {%- set tools = none %}\n", - "{%- endif %}\n", - "\n", - "{#- This block extracts the system message, so we can slot it into the right place. #}\n", - "{%- if messages[0]['role'] == 'system' %}\n", - " {%- set system_message = messages[0]['content'] %}\n", - " {%- set messages = messages[1:] %}\n", - "{%- else %}\n", - " {%- set system_message = \"\" %}\n", - "{%- endif %}\n", - "\n", - "{#- System message + builtin tools #}\n", - "{{- \"<|start_header_id|>system<|end_header_id|>\n", - "\n", - "\" }}\n", - "{%- if builtin_tools is defined or tools is not none %}\n", - " {{- \"Environment: ipython\n", - "\" }}\n", - "{%- endif %}\n", - "{%- if builtin_tools is defined %}\n", - " {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n", - "\n", - "\"}}\n", - "{%- endif %}\n", - "{{- \"Cutting Knowledge Date: December 2023\n", - "\" }}\n", - "{{- \"Today Date: \" + date_string + \"\n", - "\n", - "\" }}\n", - "{%- if tools is not none and not tools_in_user_message %}\n", - " {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n", - " {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n", - " {{- \"Do not use variables.\n", - "\n", - "\" }}\n", - " {%- for t in tools %}\n", - " {{- t | tojson(indent=4) }}\n", - " {{- \"\n", - "\n", - "\" }}\n", - " {%- endfor %}\n", - "{%- endif %}\n", - "{{- system_message }}\n", - "{{- \"<|eot_id|>\" }}\n", - "\n", - "{#- Custom tools are passed in a user message with some extra guidance #}\n", - "{%- if tools_in_user_message and not tools is none %}\n", - " {#- Extract the first user message so we can plug it in here #}\n", - " {%- if messages | length != 0 %}\n", - " {%- set first_user_message = messages[0]['content'] %}\n", - " {%- set messages = messages[1:] %}\n", - " {%- else %}\n", - " {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n", - "{%- endif %}\n", - " {{- '<|start_header_id|>user<|end_header_id|>\n", - "\n", - "' -}}\n", - " {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n", - " {{- \"with its proper arguments that best answers the given prompt.\n", - "\n", - "\" }}\n", - " {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n", - " {{- \"Do not use variables.\n", - "\n", - "\" }}\n", - " {%- for t in tools %}\n", - " {{- t | tojson(indent=4) }}\n", - " {{- \"\n", - "\n", - "\" }}\n", - " {%- endfor %}\n", - " {{- first_user_message + \"<|eot_id|>\"}}\n", - "{%- endif %}\n", - "\n", - "{%- for message in messages %}\n", - " {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n", - " {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n", - "\n", - "'+ message['content'] + '<|eot_id|>' }}\n", - " {%- elif 'tool_calls' in message %}\n", - " {%- if not message.tool_calls|length == 1 %}\n", - " {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n", - " {%- endif %}\n", - " {%- set tool_call = message.tool_calls[0].function %}\n", - " {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n", - " {{- '<|start_header_id|>assistant<|end_header_id|>\n", - "\n", - "' -}}\n", - " {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n", - " {%- for arg_name, arg_val in tool_call.arguments | items %}\n", - " {{- arg_name + '=\"' + arg_val + '\"' }}\n", - " {%- if not loop.last %}\n", - " {{- \", \" }}\n", - " {%- endif %}\n", - " {%- endfor %}\n", - " {{- \")\" }}\n", - " {%- else %}\n", - " {{- '<|start_header_id|>assistant<|end_header_id|>\n", - "\n", - "' -}}\n", - " {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n", - " {{- '\"parameters\": ' }}\n", - " {{- tool_call.arguments | tojson }}\n", - " {{- \"}\" }}\n", - " {%- endif %}\n", - " {%- if builtin_tools is defined %}\n", - " {#- This means we're in ipython mode #}\n", - " {{- \"<|eom_id|>\" }}\n", - " {%- else %}\n", - " {{- \"<|eot_id|>\" }}\n", - " {%- endif %}\n", - " {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n", - " {{- \"<|start_header_id|>ipython<|end_header_id|>\n", - "\n", - "\" }}\n", - " {%- if message.content is mapping or message.content is iterable %}\n", - " {{- message.content | tojson }}\n", - " {%- else %}\n", - " {{- message.content }}\n", - " {%- endif %}\n", - " {{- \"<|eot_id|>\" }}\n", - " {%- endif %}\n", - "{%- endfor %}\n", - "{%- if add_generation_prompt %}\n", - " {{- '<|start_header_id|>assistant<|end_header_id|>\n", - "\n", - "' }}\n", - "{%- endif %}\n", - "\n", - "INFO:gguf.gguf_writer:Writing the following files:\n", - "INFO:gguf.gguf_writer:/content/model/unsloth.F16.gguf: n_tensors = 147, total_size = 2.5G\n", - "Writing: 100%|██████████| 2.47G/2.47G [00:36<00:00, 67.9Mbyte/s]\n", - "INFO:hf-to-gguf:Model successfully exported to /content/model/unsloth.F16.gguf\n", - "Unsloth: Conversion completed! Output location: /content/model/unsloth.F16.gguf\n", - "Unsloth: [2] Converting GGUF 16bit into q4_k_m. This might take 20 minutes...\n", - "main: build = 5836 (b9c3eefd)\n", - "main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu\n", - "main: quantizing '/content/model/unsloth.F16.gguf' to '/content/model/unsloth.Q4_K_M.gguf' as Q4_K_M using 4 threads\n", - "llama_model_loader: loaded meta data with 29 key-value pairs and 147 tensors from /content/model/unsloth.F16.gguf (version GGUF V3 (latest))\n", - "llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.\n", - "llama_model_loader: - kv 0: general.architecture str = llama\n", - "llama_model_loader: - kv 1: general.type str = model\n", - "llama_model_loader: - kv 2: general.name str = Model\n", - "llama_model_loader: - kv 3: general.size_label str = 1.2B\n", - "llama_model_loader: - kv 4: llama.block_count u32 = 16\n", - "llama_model_loader: - kv 5: llama.context_length u32 = 131072\n", - "llama_model_loader: - kv 6: llama.embedding_length u32 = 2048\n", - "llama_model_loader: - kv 7: llama.feed_forward_length u32 = 8192\n", - "llama_model_loader: - kv 8: llama.attention.head_count u32 = 32\n", - "llama_model_loader: - kv 9: llama.attention.head_count_kv u32 = 8\n", - "llama_model_loader: - kv 10: llama.rope.freq_base f32 = 500000.000000\n", - "llama_model_loader: - kv 11: llama.attention.layer_norm_rms_epsilon f32 = 0.000010\n", - "llama_model_loader: - kv 12: llama.attention.key_length u32 = 64\n", - "llama_model_loader: - kv 13: llama.attention.value_length u32 = 64\n", - "llama_model_loader: - kv 14: general.file_type u32 = 1\n", - "llama_model_loader: - kv 15: llama.vocab_size u32 = 128256\n", - "llama_model_loader: - kv 16: llama.rope.dimension_count u32 = 64\n", - "llama_model_loader: - kv 17: general.quantization_version u32 = 2\n", - "llama_model_loader: - kv 18: tokenizer.ggml.model str = gpt2\n", - "llama_model_loader: - kv 19: tokenizer.ggml.pre str = llama-bpe\n", - "llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,128256] = [\"!\", \"\\\"\", \"#\", \"$\", \"%\", \"&\", \"'\", ...\n", - "llama_model_loader: - kv 21: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...\n", - "llama_model_loader: - kv 22: tokenizer.ggml.merges arr[str,280147] = [\"Ġ Ġ\", \"Ġ ĠĠĠ\", \"ĠĠ ĠĠ\", \"...\n", - "llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 128000\n", - "llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 128009\n", - "llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 128004\n", - "llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true\n", - "llama_model_loader: - kv 27: tokenizer.ggml.add_sep_token bool = false\n", - "llama_model_loader: - kv 28: tokenizer.chat_template str = {{- bos_token }}\\n{%- if custom_tools ...\n", - "llama_model_loader: - type f32: 34 tensors\n", - "llama_model_loader: - type f16: 113 tensors\n", - "[ 1/ 147] output_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 2/ 147] rope_freqs.weight - [ 32, 1, 1, 1], type = f32, size = 0.000 MB\n", - "[ 3/ 147] token_embd.weight - [ 2048, 128256, 1, 1], type = f16, converting to q6_K .. size = 501.00 MiB -> 205.49 MiB\n", - "[ 4/ 147] blk.0.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 5/ 147] blk.0.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 6/ 147] blk.0.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 7/ 147] blk.0.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 8/ 147] blk.0.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 9/ 147] blk.0.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 10/ 147] blk.0.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 11/ 147] blk.0.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 12/ 147] blk.0.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 13/ 147] blk.1.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 14/ 147] blk.1.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 15/ 147] blk.1.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 16/ 147] blk.1.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 17/ 147] blk.1.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 18/ 147] blk.1.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 19/ 147] blk.1.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 20/ 147] blk.1.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 21/ 147] blk.1.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 22/ 147] blk.2.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 23/ 147] blk.2.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 24/ 147] blk.2.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 25/ 147] blk.2.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 26/ 147] blk.2.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 27/ 147] blk.2.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 28/ 147] blk.2.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 29/ 147] blk.2.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 30/ 147] blk.2.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 31/ 147] blk.3.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 32/ 147] blk.3.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 33/ 147] blk.3.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 34/ 147] blk.3.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 35/ 147] blk.3.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 36/ 147] blk.3.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 37/ 147] blk.3.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 38/ 147] blk.3.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 39/ 147] blk.3.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 40/ 147] blk.4.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 41/ 147] blk.4.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 42/ 147] blk.4.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 43/ 147] blk.4.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 44/ 147] blk.4.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 45/ 147] blk.4.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 46/ 147] blk.4.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 47/ 147] blk.4.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 48/ 147] blk.4.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 49/ 147] blk.5.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 50/ 147] blk.5.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 51/ 147] blk.5.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 52/ 147] blk.5.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 53/ 147] blk.5.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 54/ 147] blk.5.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 55/ 147] blk.5.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 56/ 147] blk.5.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 57/ 147] blk.5.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 58/ 147] blk.6.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 59/ 147] blk.6.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 60/ 147] blk.6.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 61/ 147] blk.6.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 62/ 147] blk.6.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 63/ 147] blk.6.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 64/ 147] blk.6.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 65/ 147] blk.6.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 66/ 147] blk.6.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 67/ 147] blk.7.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 68/ 147] blk.7.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 69/ 147] blk.7.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 70/ 147] blk.7.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 71/ 147] blk.7.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 72/ 147] blk.7.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 73/ 147] blk.7.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 74/ 147] blk.7.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 75/ 147] blk.7.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 76/ 147] blk.8.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 77/ 147] blk.8.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 78/ 147] blk.8.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 79/ 147] blk.8.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 80/ 147] blk.8.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 81/ 147] blk.8.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 82/ 147] blk.8.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 83/ 147] blk.8.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 84/ 147] blk.8.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 85/ 147] blk.9.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 86/ 147] blk.9.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 87/ 147] blk.9.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 88/ 147] blk.9.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 89/ 147] blk.9.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 90/ 147] blk.9.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 91/ 147] blk.9.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 92/ 147] blk.9.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 93/ 147] blk.9.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 94/ 147] blk.10.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 95/ 147] blk.10.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 96/ 147] blk.10.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 97/ 147] blk.10.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 98/ 147] blk.10.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 99/ 147] blk.10.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 100/ 147] blk.10.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 101/ 147] blk.10.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 102/ 147] blk.10.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 103/ 147] blk.11.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 104/ 147] blk.11.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 105/ 147] blk.11.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 106/ 147] blk.11.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 107/ 147] blk.11.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 108/ 147] blk.11.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 109/ 147] blk.11.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 110/ 147] blk.11.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 111/ 147] blk.11.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 112/ 147] blk.12.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 113/ 147] blk.12.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 114/ 147] blk.12.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 115/ 147] blk.12.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 116/ 147] blk.12.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 117/ 147] blk.12.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 118/ 147] blk.12.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 119/ 147] blk.12.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 120/ 147] blk.12.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 121/ 147] blk.13.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 122/ 147] blk.13.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 123/ 147] blk.13.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 124/ 147] blk.13.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 125/ 147] blk.13.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 126/ 147] blk.13.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 127/ 147] blk.13.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 128/ 147] blk.13.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 129/ 147] blk.13.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 130/ 147] blk.14.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 131/ 147] blk.14.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 132/ 147] blk.14.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 133/ 147] blk.14.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 134/ 147] blk.14.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 135/ 147] blk.14.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 136/ 147] blk.14.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 137/ 147] blk.14.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 138/ 147] blk.14.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 139/ 147] blk.15.attn_k.weight - [ 2048, 512, 1, 1], type = f16, converting to q4_K .. size = 2.00 MiB -> 0.56 MiB\n", - "[ 140/ 147] blk.15.attn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 141/ 147] blk.15.attn_output.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 142/ 147] blk.15.attn_q.weight - [ 2048, 2048, 1, 1], type = f16, converting to q4_K .. size = 8.00 MiB -> 2.25 MiB\n", - "[ 143/ 147] blk.15.attn_v.weight - [ 2048, 512, 1, 1], type = f16, converting to q6_K .. size = 2.00 MiB -> 0.82 MiB\n", - "[ 144/ 147] blk.15.ffn_down.weight - [ 8192, 2048, 1, 1], type = f16, converting to q6_K .. size = 32.00 MiB -> 13.12 MiB\n", - "[ 145/ 147] blk.15.ffn_gate.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "[ 146/ 147] blk.15.ffn_norm.weight - [ 2048, 1, 1, 1], type = f32, size = 0.008 MB\n", - "[ 147/ 147] blk.15.ffn_up.weight - [ 2048, 8192, 1, 1], type = f16, converting to q4_K .. size = 32.00 MiB -> 9.00 MiB\n", - "llama_model_quantize_impl: model size = 2357.26 MB\n", - "llama_model_quantize_impl: quant size = 762.81 MB\n", - "\n", - "main: quantize time = 122938.19 ms\n", - "main: total time = 122938.19 ms\n", - "Unsloth: Conversion completed! Output location: /content/model/unsloth.Q4_K_M.gguf\n", - "Unsloth: Saved Ollama Modelfile to model/Modelfile\n" - ] - } - ] - }, - { - "cell_type": "code", - "source": [ - "from google.colab import drive\n", - "drive.mount('/content/drive')\n", - "import shutil\n", - "\n", - "\n", - "model_path = '/content/model/unsloth.Q4_K_M.gguf'\n", - "drive_folder = '/content/drive/My Drive/Model1Folder/'\n", - "\n", - "shutil.move(model_path, drive_folder)" - ], - "metadata": { - "id": "sq42iNB-Z-j1", - "outputId": "57b836c8-a97d-4074-cfb1-feca4f2b4e15", - "colab": { - "base_uri": "https://localhost:8080/", - "height": 53 - } - }, - "execution_count": 19, - "outputs": [ - { - "output_type": "stream", - "name": "stdout", - "text": [ - "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n" - ] - }, - { - "output_type": "execute_result", - "data": { - "text/plain": [ - "'/content/drive/My Drive/Model1Folder/unsloth.Q4_K_M.gguf'" - ], - "application/vnd.google.colaboratory.intrinsic+json": { - "type": "string" - } - }, - "metadata": {}, - "execution_count": 19 - } - ] - } - ], - "metadata": { - "accelerator": "GPU", - "colab": { - "gpuType": "T4", - "provenance": [] - }, - "kernelspec": { - "display_name": "Python 3", - "name": "python3" - }, - "language_info": { - "name": "python" - }, - "widgets": { - "application/vnd.jupyter.widget-state+json": { - "974c4eb606864332b3e99b158e5c2248": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_fb0a8933009d47db891f46fe7b5004e5", - "IPY_MODEL_cb02d10b76254e73b3c49f2f11b57269", - "IPY_MODEL_b4d1e9f1cb0f46babe6ce0e026d8565a" - ], - "layout": "IPY_MODEL_8000159229ca4b1785ecb4683a282e49" - } - }, - "fb0a8933009d47db891f46fe7b5004e5": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_35efbf67792d4a7f9a253d633451563a", - "placeholder": "​", - "style": "IPY_MODEL_ba859ed12a6245d2bf839087217cabe3", - "value": "Map: 100%" - } - }, - "cb02d10b76254e73b3c49f2f11b57269": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_00b8f1da5e5e4f15a562fb07a6259481", - "max": 105851, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_cc5f0f02fff2499e977b505037a3d6f6", - "value": 105851 - } - }, - "b4d1e9f1cb0f46babe6ce0e026d8565a": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_6f15880e16514ab5844763b1d45a85f7", - "placeholder": "​", - "style": "IPY_MODEL_889be39cf43042549042e31fdc438e7f", - "value": " 105851/105851 [00:18<00:00, 7318.61 examples/s]" - } - }, - "8000159229ca4b1785ecb4683a282e49": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "35efbf67792d4a7f9a253d633451563a": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "ba859ed12a6245d2bf839087217cabe3": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "00b8f1da5e5e4f15a562fb07a6259481": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "cc5f0f02fff2499e977b505037a3d6f6": { - "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "6f15880e16514ab5844763b1d45a85f7": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "889be39cf43042549042e31fdc438e7f": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "73464bc430fa471c9da348275de32220": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_42362451ce674deab324dd571e2e63a8", - "IPY_MODEL_9dfde51c9a794aa7bb96e260aae71756", - "IPY_MODEL_37837a2b2aae45369edab2d9b84e2f40" - ], - "layout": "IPY_MODEL_110a65ffc5e54f799f98dcace707e3c3" - } - }, - "42362451ce674deab324dd571e2e63a8": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_b3a4f1e5e2b349f0bc9af660047c5947", - "placeholder": "​", - "style": "IPY_MODEL_b68154275bad4c81aa427f4981b5fb1b", - "value": "Unsloth: Tokenizing ["text"]: 100%" - } - }, - "9dfde51c9a794aa7bb96e260aae71756": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_73930cb531bb4e0286b9530fa1e26be2", - "max": 105851, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_9eba57bbcec94d9c871704856fb7e1d1", - "value": 105851 - } - }, - "37837a2b2aae45369edab2d9b84e2f40": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_11097e54c5314914a0a65c0b0ec1bcbb", - "placeholder": "​", - "style": "IPY_MODEL_462bf508424840309de35c510cd41be6", - "value": " 105851/105851 [01:17<00:00, 1921.88 examples/s]" - } - }, - "110a65ffc5e54f799f98dcace707e3c3": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "b3a4f1e5e2b349f0bc9af660047c5947": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "b68154275bad4c81aa427f4981b5fb1b": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "73930cb531bb4e0286b9530fa1e26be2": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "9eba57bbcec94d9c871704856fb7e1d1": { - "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "11097e54c5314914a0a65c0b0ec1bcbb": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "462bf508424840309de35c510cd41be6": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "85d3e396d5a944e1a6b7f52ada151f20": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HBoxModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HBoxModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HBoxView", - "box_style": "", - "children": [ - "IPY_MODEL_306968a12f004b239b12bb388c5ac60d", - "IPY_MODEL_3e79f19c2d554d8c8660e77b6a670e07", - "IPY_MODEL_3c6ffaff3ed4427086ad3faabee5eb2a" - ], - "layout": "IPY_MODEL_20bc91381af149c3a4db7953bac757a9" - } - }, - "306968a12f004b239b12bb388c5ac60d": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_9032fc0aae5048338f3cf7c5128f286a", - "placeholder": "​", - "style": "IPY_MODEL_045df3567d80438486b553c17281e955", - "value": "Map (num_proc=2): 100%" - } - }, - "3e79f19c2d554d8c8660e77b6a670e07": { - "model_module": "@jupyter-widgets/controls", - "model_name": "FloatProgressModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "FloatProgressModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "ProgressView", - "bar_style": "success", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_ceee3c9296a545e0a3fc4a37c78b473a", - "max": 105851, - "min": 0, - "orientation": "horizontal", - "style": "IPY_MODEL_5ba9d0d0cc564eb29832e6ee2ad57eda", - "value": 105851 - } - }, - "3c6ffaff3ed4427086ad3faabee5eb2a": { - "model_module": "@jupyter-widgets/controls", - "model_name": "HTMLModel", - "model_module_version": "1.5.0", - "state": { - "_dom_classes": [], - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "HTMLModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/controls", - "_view_module_version": "1.5.0", - "_view_name": "HTMLView", - "description": "", - "description_tooltip": null, - "layout": "IPY_MODEL_b1d1541ca63f4b4383e8b0644d8a7b9f", - "placeholder": "​", - "style": "IPY_MODEL_74c5c9c611b8457a946e9e92e22dc560", - "value": " 105851/105851 [00:19<00:00, 4736.82 examples/s]" - } - }, - "20bc91381af149c3a4db7953bac757a9": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "9032fc0aae5048338f3cf7c5128f286a": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "045df3567d80438486b553c17281e955": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - }, - "ceee3c9296a545e0a3fc4a37c78b473a": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "5ba9d0d0cc564eb29832e6ee2ad57eda": { - "model_module": "@jupyter-widgets/controls", - "model_name": "ProgressStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "ProgressStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "bar_color": null, - "description_width": "" - } - }, - "b1d1541ca63f4b4383e8b0644d8a7b9f": { - "model_module": "@jupyter-widgets/base", - "model_name": "LayoutModel", - "model_module_version": "1.2.0", - "state": { - "_model_module": "@jupyter-widgets/base", - "_model_module_version": "1.2.0", - "_model_name": "LayoutModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "LayoutView", - "align_content": null, - "align_items": null, - "align_self": null, - "border": null, - "bottom": null, - "display": null, - "flex": null, - "flex_flow": null, - "grid_area": null, - "grid_auto_columns": null, - "grid_auto_flow": null, - "grid_auto_rows": null, - "grid_column": null, - "grid_gap": null, - "grid_row": null, - "grid_template_areas": null, - "grid_template_columns": null, - "grid_template_rows": null, - "height": null, - "justify_content": null, - "justify_items": null, - "left": null, - "margin": null, - "max_height": null, - "max_width": null, - "min_height": null, - "min_width": null, - "object_fit": null, - "object_position": null, - "order": null, - "overflow": null, - "overflow_x": null, - "overflow_y": null, - "padding": null, - "right": null, - "top": null, - "visibility": null, - "width": null - } - }, - "74c5c9c611b8457a946e9e92e22dc560": { - "model_module": "@jupyter-widgets/controls", - "model_name": "DescriptionStyleModel", - "model_module_version": "1.5.0", - "state": { - "_model_module": "@jupyter-widgets/controls", - "_model_module_version": "1.5.0", - "_model_name": "DescriptionStyleModel", - "_view_count": null, - "_view_module": "@jupyter-widgets/base", - "_view_module_version": "1.2.0", - "_view_name": "StyleView", - "description_width": "" - } - } - } - } - }, - "nbformat": 4, - "nbformat_minor": 0 -} \ No newline at end of file