question stringlengths 670 690 | answer stringclasses 1
value | task_config stringclasses 1
value | task_source stringclasses 1
value | prompt listlengths 2 2 | letters stringlengths 4 8 | source stringlengths 4 4 | length int64 4 8 | prompt__example_annotation__metadata dict | __index_level_0__ int64 0 23.2k | model_responses__example_annotation listlengths 1 1 | model_responses__example_annotation__eval_is_correct listlengths 1 1 | model_responses__example_annotation__eval_extracted_answers listlengths 1 1 | prompt_variant stringclasses 4
values | reflection_prompt listlengths 2 2 | model_responses__mutated_prompts_reflection listlengths 4 4 | model_responses__mutated_prompts_reflection__finish_reason_length_flags listlengths 4 4 | model_responses__mutated_prompts_reflection__length_partial_responses listlengths 4 4 | reflection_prompt__mutated_prompts_reflection__metadata dict | model_responses__mutated_prompts_reflection__metadata dict |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"To solve this problem, we need to find the longest word that can be formed using only the given letters and satisfies the given conditions.\n\nStep 1: Identify all possible words that can be formed using the given letters.\n - Possible words could include \"stop\", \"dot\", etc., but let's check each one more th... | [
false
] | [
"dotlu"
] | original | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'dotlu'. First, let me check if the response uses letters from the input: 'd' is in the input, 'o' is in the input, 't' is in the input, 'l' is in the input, 'u' is in the input. The answer uses letters from the input list.\nThen, let me check if the response is at least four letters lon... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"### Step-by-Step Reasoning\n\n1. **Identify Unique Characters**: First, we need to identify all unique characters in the given list.\n - Input: ['s', 'l', 'd', 'o', 't', 'u']\n - Unique characters: {'s', 'l', 'd', 'o', 't', 'u'}\n\n2. **Check for Valid Words**:\n - We will check each possible combination of ... | [
false
] | [
"sol"
] | original | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'sol'. First, let me check if the response uses letters from the input: 's' is in the input, 'o' is in the input, 'l' is in the input. The answer uses letters from the input list.\nThen, let me check if the response is at least four letters long, yes it is since the answer is 4 letters l... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"To solve this problem, we need to follow these steps:\n\n1. **Identify the available letters**: We have the letters `['s', 'l', 'd', 'o', 't', 'u']`.\n2. **Find combinations that form valid words**: Since only four-letter words will be considered and no letter can be used more than once, we'll try all possible com... | [
false
] | [
"No valid four-letter word exists"
] | original | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'trace'. First, let me check if the response uses letters from the input: 't' is in the input, 'r' is in the input, 'a' is in the input, 'c' is not in the input, 'e' is in the input. The answer uses a letter not in the input list.\nThen, let me check if the response is at least four lett... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"### Step-by-Step Reasoning\n\n1. **Identify Unique Letters**:\n - We have the letters `['s', 'l', 'd', 'o', 't', 'u']`.\n - These letters appear only once each.\n\n2. **Form Possible Words**:\n - Since all letters are unique and can form words, we need to find combinations that meet our criteria.\n \n3. **... | [
false
] | [
"slodut"
] | original | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'slodut'.\n\nFirst, let me check if the response uses letters from the input: 's' is in the input, 'l' is in the input, 'o' is in the input, 'd' is in the input, 't' is in the input, 'u' is in the input. The answer uses letters from the input list.\n\nThen, let me check if the response i... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"### Problem\n\nGiven a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:\n\n1) Only use the letters in the input to create a word.\n2) Only give one word as the answer.\n3) The word should be at least 4 characters long.\n\nFor example: If the input ... | [
false
] | [
"spotlight"
] | plan_and_execute | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'spotlight'. First, let me check if the response uses letters from the input: 'p', 'o', 't', 'l', 'i', 'c', 'k', 'h', 'a' are all present in the input list. The answer does use letters from the input list.\nThen, let me check if the response is at least four letters long, yes it is since... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"### Plan\n\n**Step 1:** Identify all possible combinations of the given letters.\n- The given letters are: `['s', 'l', 'd', 'o', 't', 'u']`.\n- We need to find words using these letters.\n\n**Step 2:** Generate all permutations of each combination.\n- Since there are 6 letters, we will generate all permutations of... | [
false
] | [
"student"
] | plan_and_execute | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'student'. First, let me check if the response uses letters from the input: 's' is in the input, 't' is in the input, 'u' is in the input, 'd' is in the input, 'e' is in the input, 't' is in the input. The answer uses letters from the input list. Then, let me check if the response is at ... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"### Problem\n\n**Input:** ['s', 'l', 'd', 'o', 't', 'u']\n\n**Goal:** Rearrange the given letters to form a valid English word.\n\n### High-Level Plan\n\n1. **Understand the Input**: Analyze the provided list of letters.\n2. **Identify Possible Words**: Explore combinations of the letters to find words.\n3. **Vali... | [
false
] | [
"slodu"
] | plan_and_execute | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'slodu'.\n\nFirst, let me check if the response uses letters from the input: 's', 'l', 'd', 'o', 't', 'u' are all present in the input.\n\nNext, I'll check if the response is at least four letters long. 'slodu' indeed has five letters, which meets the requirement.\n\nFinally, I'll confir... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"### Problem\n\nGiven a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:\n\n1. **Only use the letters in the input to create a word.** \n - This means no additional letters from other sources can be used.\n\n2. **Only give one word as the answer.... | [
false
] | [
"stool"
] | plan_and_execute | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer:\n\nFirst, let me check if the response uses letters from the input: 's' is in the input, 't' is in the input, 'r' is in the input, 'e' is in the input, 'a' is in the input. The answer uses letters from the input list.\n\nThen, let me check if the response is at least four letters long, y... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"Rewritten Question:\nGiven a set of letters, determine the longest possible word that can be formed using these letters.\n\nNow let's analyze the given letters: {'s', 'l', 'd', 'o', 't', 'u'}\n\nTo find the longest word, we need to consider all permutations of these letters and identify the ones that form valid wo... | [
false
] | [
"slow"
] | rephrase | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer: 'slow'.\n\nFirst, let me check if the response uses letters from the input: 's' is in the input, 'l' is in the input, 'o' is in the input, 'w' is not in the input, 'e' is in the input. The answer uses a letter not in the input list.\n\nThen, let me check if the response is at least four ... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} | |
Answer the following problem. Explain your reasoning step by step. When you are finished, give your answer in this format: <answer> (your answer) </answer>.
### Problem
Given a list of letters, rearrange the letters to create a valid English word. You should satisfy the following conditions:
1) Only use the lette... | letter_countdown_4o | letter_countdown | [
{
"content": "You like to solve problems by thinking step by step. Write out your reasoning then give your answer in \"<answer>\n(your answer)\n</answer>\". You always end with </answer>, you never ever end without giving an answer.",
"role": "system"
},
{
"content": "Answer the following problem. E... | sldotu | tous | 6 | {
"api_url": "http://127.0.0.1:43271",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 4096,
"n": 3,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwe... | 0 | [
"Rewritten Question: \nGiven a list of letters, rearrange the letters to form the longest possible English word using only the given letters.\n\nStep-by-step reasoning:\n1. Identify all unique letters in the input.\n2. Determine which combination of these letters forms the longest word that meets the criteria (at l... | [
false
] | [
"stlodut"
] | rephrase | [
{
"content": "You think step by step and reflect on the given answer for the question reasoning about if the answer was correct or incorrect. You then always say <verdict>\ncorrect\n</verdict> or <verdict>\nincorrect\n</verdict> depending on if the answer was correct or incorrect in your opinion according to yo... | [
"Let us verify this answer:\n\n1. **Letters in Input**: {'s', 'l', 'd', 'o', 't', 'u'}\n2. **Word Length**: At least 4 characters\n3. **English Word Check**: 'stlodut' is a valid English word.\n\n**Verification**:\n- All letters from the input list ('s', 'l', 'd', 'o', 't', 'u') are used in 'stlodut'.\n- The word '... | [
false,
false,
false,
false
] | [
"",
"",
"",
""
] | {
"api_url": "http://127.0.0.1:41045",
"backend": "litellm",
"chat_template_applied": true,
"generation_params": {
"chat_template_applied": true,
"max_tokens": 512,
"n": 4,
"repetition_penalty": 1.1,
"temperature": 0.7,
"top_k": 20,
"top_p": 0.8
},
"model_name": "hosted_vllm/Qwen... | {
"backend": "litellm",
"model_name": "hosted_vllm/Qwen/Qwen2.5-1.5B-Instruct",
"n_responses": 4
} |
End of preview. Expand in Data Studio
README.md exists but content is empty.
- Downloads last month
- 1