diff --git "a/03-poe-token-count-exploration.ipynb" "b/03-poe-token-count-exploration.ipynb" --- "a/03-poe-token-count-exploration.ipynb" +++ "b/03-poe-token-count-exploration.ipynb" @@ -28,8 +28,8 @@ }, "outputs": [], "source": [ - "INPUT_DATASET = 'derek-thomas/labeled-multiple-choice-explained-mistral-tokenized'\n", - "BASE_MODEL = 'mistralai/Mistral-7B-Instruct-v0.3'" + "INPUT_DATASET = 'derek-thomas/labeled-multiple-choice-explained-falcon-tokenized'\n", + "BASE_MODEL = 'tiiuae/Falcon3-7B-Instruct'" ] }, { @@ -49,7 +49,7 @@ { "data": { "application/vnd.jupyter.widget-view+json": { - "model_id": "d675da3076694064ba0c69ed97f938f8", + "model_id": "2c216b161c3340ada0223141da2cc441", "version_major": 2, "version_minor": 0 }, @@ -71,78 +71,7 @@ "execution_count": 3, "id": "a9e2d29c-1f8e-4a70-839f-f61ae396d6f6", "metadata": {}, - "outputs": [ - { - "data": { - "application/vnd.jupyter.widget-view+json": { - "model_id": "dd06a12730fa4af1b863273c333c6a4c", - "version_major": 2, - "version_minor": 0 - }, - "text/plain": [ - "README.md: 0%| | 0.00/1.18k [00:00[INST] Answer the Question and include your Reasoning and the Final Answer in a json like: {\"Reasoning: \"...\", \"Final Answer\": \"x\"} where x is a letter that corresponds to the answer choice which is a letter between a and h.\\nQuestion: What can genetic material have?\\nAnswer Choices: (a) Resistance (b) Mutations (c) Clorophyll (d) Nucleotide (e) Symmetry (f) Allow growth (g) Contamination (h) Warmth[/INST] {\\'Reasoning\\': \\'a) Resistance: Genetic material can carry genes that provide resistance to certain diseases or environmental factors, but this is not a characteristic of genetic material itself. Therefore, this option is incorrect.\\\\n\\\\nc) Chlorophyll: Chlorophyll is a pigment found in plants that is responsible for photosynthesis. It is not a characteristic of genetic material. Therefore, this option is incorrect.\\\\n\\\\nd) Nucleotide: Nucleotides are the building blocks of DNA and RNA, which are types of genetic material. However, this option is too broad and does not fully answer the question. Therefore, this option is incorrect.\\\\n\\\\ne) Symmetry: Symmetry is a characteristic of physical objects and organisms, but it is not a characteristic of genetic material. Therefore, this option is incorrect.\\\\n\\\\nf) Allow growth: Genetic material provides the instructions for the growth and development of organisms, but it is not a characteristic of genetic material itself. Therefore, this option is incorrect.\\\\n\\\\ng) Contamination: Contamination is the presence of unwanted substances or impurities, and it is not a characteristic of genetic material. Therefore, this option is incorrect.\\\\n\\\\nh) Warmth: Warmth is a physical property of objects and is not related to genetic material. Therefore, this option is incorrect.\\\\n\\\\nIn conclusion, the only option that correctly describes a characteristic of genetic material is b) mutations. Genetic material can have mutations, which are changes in the DNA sequence that can lead to genetic variation and evolution.\\', \\'Final Answer\\': \\'b\\'}'" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], - "source": [ - "df['conversation_RFA_sg_gpt3_5'].iloc[0]" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "0dc985d7-32e3-413f-8640-55829da19838", - "metadata": {}, - "outputs": [ - { - "data": { - "text/plain": [ - "[4]" + "array([{'content': 'Answer the Question and include your reasoning and the final answer in a json like: {\"reasoning\": , \"final_answer\": }.', 'role': 'system'},\n", + " {'content': 'Question: What can genetic material have?\\nAnswer Choices: (a) Resistance (b) Mutations (c) Clorophyll (d) Nucleotide (e) Symmetry (f) Allow growth (g) Contamination (h) Warmth', 'role': 'user'},\n", + " {'content': \"{'reasoning': 'a) Resistance: Genetic material can carry genes that provide resistance to certain diseases or environmental factors, but this is not a characteristic of genetic material itself. Therefore, this option is incorrect.\\\\n\\\\nc) Chlorophyll: Chlorophyll is a pigment found in plants that is responsible for photosynthesis. It is not a characteristic of genetic material. Therefore, this option is incorrect.\\\\n\\\\nd) Nucleotide: Nucleotides are the building blocks of DNA and RNA, which are types of genetic material. However, this option is too broad and does not fully answer the question. Therefore, this option is incorrect.\\\\n\\\\ne) Symmetry: Symmetry is a characteristic of physical objects and organisms, but it is not a characteristic of genetic material. Therefore, this option is incorrect.\\\\n\\\\nf) Allow growth: Genetic material provides the instructions for the growth and development of organisms, but it is not a characteristic of genetic material itself. Therefore, this option is incorrect.\\\\n\\\\ng) Contamination: Contamination is the presence of unwanted substances or impurities, and it is not a characteristic of genetic material. Therefore, this option is incorrect.\\\\n\\\\nh) Warmth: Warmth is a physical property of objects and is not related to genetic material. Therefore, this option is incorrect.\\\\n\\\\nIn conclusion, the only option that correctly describes a characteristic of genetic material is b) mutations. Genetic material can have mutations, which are changes in the DNA sequence that can lead to genetic variation and evolution.', 'final_answer': 'b'}\", 'role': 'assistant'}],\n", + " dtype=object)" ] }, - "execution_count": 6, + "execution_count": 4, "metadata": {}, "output_type": "execute_result" } ], "source": [ - "tokenizer.encode('[/INST]', add_special_tokens=False)" + "df['conversation_RFA_gpt3_5'].iloc[0]" ] }, { "cell_type": "code", - "execution_count": 8, - "id": "bc9b3856-7652-483c-8dbc-2b9bdc85f9d7", + "execution_count": 5, + "id": "7c18dcbb-9dba-4154-8cb2-b678215a293a", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "[1, 3, 27075, 1040, 23246, 1072, 3792, 1342, 2066, 2180, 1056, 1072, 1040, 10990, 27075, 1065, 1032, 8379, 1505, 29515, 10598, 20569, 1056, 29515, 1113, 1869, 1316, 1113, 18268, 27075, 2032, 1113, 29512, 18163, 1738, 2086, 1117, 1032, 6266, 1137, 17303, 1066, 1040, 5140, 5550, 1458, 1117, 1032, 6266, 2212, 1032, 1072, 1063, 29491, 781, 25762, 29515, 2592, 1309, 20637, 4156, 1274, 29572, 781, 3588, 17749, 26173, 1982, 29515, 1093, 29476, 29499, 2760, 5400, 1093, 29494, 29499, 17737, 1465, 1093, 29485, 29499, 2134, 1039, 3894, 20298, 1093, 29483, 29499, 1186, 2253, 1059, 1090, 1315, 1093, 29474, 29499, 13124, 17409, 1093, 29490, 29499, 26780, 6825, 1093, 29489, 29499, 3767, 26682, 1093, 29484, 29499, 1162, 2553, 1130, 4, 12780, 20569, 1056, 2637, 1232, 29476, 29499, 2760, 5400, 29515, 7010, 11130, 4156, 1309, 7864, 24971, 1137, 3852, 13336, 1066, 3320, 19025, 1210, 13275, 9380, 29493, 1330, 1224, 1117, 1227, 1032, 18613, 1070, 20637, 4156, 4605, 29491, 9237, 29493, 1224, 4319, 1117, 17158, 6691, 29479, 29524, 15538, 29499, 1457, 6406, 3894, 20298, 29515, 1457, 6406, 3894, 20298, 1117, 1032, 19726, 1234, 2187, 1065, 10691, 1137, 1117, 8100, 1122, 9654, 29492, 1216, 22305, 29491, 1429, 1117, 1227, 1032, 18613, 1070, 20637, 4156, 29491, 9237, 29493, 1224, 4319, 1117, 17158, 6691, 29479, 29524, 1060, 29499, 1186, 2253, 1059, 1090, 1315, 29515, 1186, 2253, 1059, 1090, 2694, 1228, 1040, 4435, 10246, 1070, 16775, 1072, 1167, 4152, 29493, 1458, 1228, 5282, 1070, 20637, 4156, 29491, 3761, 29493, 1224, 4319, 1117, 2136, 6609, 1072, 2003, 1227, 6662, 5140, 1040, 3764, 29491, 9237, 29493, 1224, 4319, 1117, 17158, 6691, 29479, 29524, 1253, 29499, 13124, 17409, 29515, 13124, 17409, 1117, 1032, 18613, 1070, 6045, 7465, 1072, 2938, 11589, 29493, 1330, 1146, 1117, 1227, 1032, 18613, 1070, 20637, 4156, 29491, 9237, 29493, 1224, 4319, 1117, 17158, 6691, 29479, 29524, 24412, 29499, 26780, 6825, 29515, 7010, 11130, 4156, 6080, 1040, 12150, 1122, 1040, 6825, 1072, 4867, 1070, 2938, 11589, 29493, 1330, 1146, 1117, 1227, 1032, 18613, 1070, 20637, 4156, 4605, 29491, 9237, 29493, 1224, 4319, 1117, 17158, 6691, 29479, 29524, 1585, 29499, 3767, 26682, 29515, 3767, 26682, 1117, 1040, 7471, 1070, 13460, 8034, 1851, 9500, 1210, 3592, 1092, 1986, 29493, 1072, 1146, 1117, 1227, 1032, 18613, 1070, 20637, 4156, 29491, 9237, 29493, 1224, 4319, 1117, 17158, 6691, 29479, 29524, 25779, 29499, 1162, 2553, 1130, 29515, 1162, 2553, 1130, 1117, 1032, 6045, 4089, 1070, 7465, 1072, 1117, 1227, 5970, 1066, 20637, 4156, 29491, 9237, 29493, 1224, 4319, 1117, 17158, 6691, 29479, 29524, 29479, 1425, 13654, 29493, 1040, 1633, 4319, 1137, 13510, 14734, 1032, 18613, 1070, 20637, 4156, 1117, 1055, 29499, 5316, 1465, 29491, 7010, 11130, 4156, 1309, 1274, 5316, 1465, 29493, 1458, 1228, 5203, 1065, 1040, 16775, 8536, 1137, 1309, 2504, 1066, 20637, 19191, 1072, 10963, 13775, 1232, 18268, 27075, 2637, 1232, 29494, 15259, 2]\n" + "<|system|>\n", + "Answer the Question and include your reasoning and the final answer in a json like: {\"reasoning\": , \"final_answer\": }.\n", + "<|user|>\n", + "Question: What can genetic material have?\n", + "Answer Choices: (a) Resistance (b) Mutations (c) Clorophyll (d) Nucleotide (e) Symmetry (f) Allow growth (g) Contamination (h) Warmth\n", + "<|assistant|>\n", + "{'reasoning': 'a) Resistance: Genetic material can carry genes that provide resistance to certain diseases or environmental factors, but this is not a characteristic of genetic material itself. Therefore, this option is incorrect.\\n\\nc) Chlorophyll: Chlorophyll is a pigment found in plants that is responsible for photosynthesis. It is not a characteristic of genetic material. Therefore, this option is incorrect.\\n\\nd) Nucleotide: Nucleotides are the building blocks of DNA and RNA, which are types of genetic material. However, this option is too broad and does not fully answer the question. Therefore, this option is incorrect.\\n\\ne) Symmetry: Symmetry is a characteristic of physical objects and organisms, but it is not a characteristic of genetic material. Therefore, this option is incorrect.\\n\\nf) Allow growth: Genetic material provides the instructions for the growth and development of organisms, but it is not a characteristic of genetic material itself. Therefore, this option is incorrect.\\n\\ng) Contamination: Contamination is the presence of unwanted substances or impurities, and it is not a characteristic of genetic material. Therefore, this option is incorrect.\\n\\nh) Warmth: Warmth is a physical property of objects and is not related to genetic material. Therefore, this option is incorrect.\\n\\nIn conclusion, the only option that correctly describes a characteristic of genetic material is b) mutations. Genetic material can have mutations, which are changes in the DNA sequence that can lead to genetic variation and evolution.', 'final_answer': 'b'}<|endoftext|>\n" ] - }, - { - "data": { - "text/plain": [ - "[4]" - ] - }, - "execution_count": 8, - "metadata": {}, - "output_type": "execute_result" } ], "source": [ - "print(tokenizer.encode(df['conversation_RFA_sg_gpt3_5'].iloc[0], add_special_tokens=False))\n", - "tokenizer.encode('[/INST]', add_special_tokens=False)" + "print(tokenizer.apply_chat_template(df['conversation_RFA_gpt3_5'].iloc[0], tokenize=False))" ] }, { "cell_type": "markdown", - "id": "677e792e-a85f-448c-ab36-ed0aec84ca8e", + "id": "6c6200b3-13c2-47ae-96b9-1222073c49ec", "metadata": {}, "source": [ - "Great, we can see that there is a special token `[/INST]` that we will want to split on. We can count the tokens before and including `[/INST]` and that should be our input tokens, and the tokens after will be our output tokens.\n", + "Great, we can see that there is a special token `<|assistant|>` that we will want to split on. We can count the tokens before and including `<|assistant|>` and that should be our input tokens, and the tokens after will be our output tokens.\n", "\n", "Lets count those for each row in `conversation_RFA` and build a histogram of the results. `conversation_RFA` should be a good max since its just a reshuffle or superset of the other columns." ] }, { "cell_type": "code", - "execution_count": 20, + "execution_count": 6, + "id": "1f577945-aef9-451f-8dda-e2bc88fdcc74", + "metadata": {}, + "outputs": [], + "source": [ + "def split_and_measure(lst):\n", + " # Encode the subsequence dynamically\n", + " subsequence = tokenizer.encode('<|assistant|>', add_special_tokens=False)\n", + " \n", + " # Check if the subsequence exists in the list\n", + " for i in range(len(lst) - len(subsequence) + 1):\n", + " if lst[i:i + len(subsequence)] == subsequence:\n", + " input_length = i # Elements before the subsequence\n", + " output_length = len(lst) - input_length # Includes subsequence and everything after\n", + " return input_length, output_length\n", + " \n", + " # If the subsequence is not found\n", + " return len(lst), 0\n" + ] + }, + { + "cell_type": "code", + "execution_count": 7, "id": "3c8cd920-4d58-4b1d-b172-098c35dcdfbf", "metadata": { "scrolled": true @@ -259,34 +187,26 @@ "dataset = load_dataset(INPUT_DATASET, split='test')\n", "df = dataset.to_pandas()\n", "\n", - "df_token_gpt3_5 = df[['conversation_RFA_sg_gpt3_5']].copy()\n", - "df_token_gpt3_5['tokens_gpt3_5'] = df['conversation_RFA_sg_gpt3_5'].apply(lambda x: tokenizer.encode(x))\n", + "df_token_gpt3_5 = df[['conversation_RFA_gpt3_5']].copy()\n", + "df_token_gpt3_5['tokens_gpt3_5'] = df['conversation_RFA_gpt3_5'].apply(lambda x: tokenizer.apply_chat_template(x))\n", "\n", - "df_token_mistral = df[['conversation_RFA_sg_mistral']].copy()\n", - "df_token_mistral['tokens_mistral'] = df['conversation_RFA_sg_mistral'].apply(lambda x: tokenizer.encode(x))\n", + "df_token_falcon = df[['conversation_RFA_falcon']].copy()\n", + "df_token_falcon['tokens_falcon'] = df['conversation_RFA_falcon'].apply(lambda x: tokenizer.apply_chat_template(x))\n", "\n", - "def split_and_measure(lst):\n", - " if 4 in lst:\n", - " index_of_4 = lst.index(4)\n", - " length_before = index_of_4 + 1 # Including 4\n", - " length_after = len(lst) - length_before\n", - " return length_before, length_after\n", - " else:\n", - " return None, len(lst) # If 4 is not present\n", "\n", "df_token_gpt3_5[['input_tokens', 'output_tokens']] = df_token_gpt3_5['tokens_gpt3_5'].apply(split_and_measure).apply(pd.Series)\n", - "df_token_mistral[['input_tokens', 'output_tokens']] = df_token_mistral['tokens_mistral'].apply(split_and_measure).apply(pd.Series)" + "df_token_falcon[['input_tokens', 'output_tokens']] = df_token_falcon['tokens_falcon'].apply(split_and_measure).apply(pd.Series)" ] }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 8, "id": "9b23b7a3-5448-4b2e-9253-5d1b66ef1e0a", "metadata": {}, "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -319,7 +239,7 @@ }, { "cell_type": "code", - "execution_count": 23, + "execution_count": 9, "id": "9d81d486-bafd-454b-9a44-934ec111ad4d", "metadata": {}, "outputs": [ @@ -327,8 +247,8 @@ "name": "stdout", "output_type": "stream", "text": [ - "Our Max Input Tokens:\t162\n", - "Our Max Output Tokens:\t572\n" + "Our Max Input Tokens:\t155\n", + "Our Max Output Tokens:\t538\n" ] } ], @@ -338,21 +258,13 @@ }, { "cell_type": "code", - "execution_count": null, - "id": "e6e235c3-75f4-48dd-b0cb-d7cc42426e69", - "metadata": {}, - "outputs": [], - "source": [] - }, - { - "cell_type": "code", - "execution_count": 24, + "execution_count": 10, "id": "7dea222b-a974-4ff6-9e3c-07de766b76c4", "metadata": {}, "outputs": [ { "data": { - "image/png": "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", + "image/png": "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", "text/plain": [ "
" ] @@ -368,10 +280,10 @@ "plt.figure(figsize=(10, 6))\n", "\n", "# Histogram for Input Tokens\n", - "plt.hist(df_token_mistral['input_tokens'], bins=10, alpha=0.6, label='Input Tokens')\n", + "plt.hist(df_token_falcon['input_tokens'], bins=10, alpha=0.6, label='Input Tokens')\n", "\n", "# Histogram for Output Tokens\n", - "plt.hist(df_token_mistral['output_tokens'], bins=10, alpha=0.6, label='Output Tokens')\n", + "plt.hist(df_token_falcon['output_tokens'], bins=10, alpha=0.6, label='Output Tokens')\n", "\n", "# Add titles and labels\n", "plt.title(\"Token Summary\")\n", @@ -385,7 +297,7 @@ }, { "cell_type": "code", - "execution_count": 26, + "execution_count": 11, "id": "d6a78d92-2fc4-4354-8825-b17cba59eee4", "metadata": {}, "outputs": [ @@ -393,13 +305,13 @@ "name": "stdout", "output_type": "stream", "text": [ - "Our Max Input Tokens:\t162\n", - "Our Max Output Tokens:\t1148\n" + "Our Max Input Tokens:\t155\n", + "Our Max Output Tokens:\t1535\n" ] } ], "source": [ - "print(f\"Our Max Input Tokens:\\t{max(df_token_mistral.input_tokens)}\\nOur Max Output Tokens:\\t{max(df_token_mistral.output_tokens)}\")" + "print(f\"Our Max Input Tokens:\\t{max(df_token_falcon.input_tokens)}\\nOur Max Output Tokens:\\t{max(df_token_falcon.output_tokens)}\")" ] }, { @@ -427,7 +339,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.11.10" + "version": "3.11.11" } }, "nbformat": 4,