ProCreations/grug-35b-v2
Text Generation • 35B • Updated • 382 • 8
id stringlengths 10 56 | source stringclasses 11
values | loss_mode stringclasses 2
values | train_last_only bool 2
classes | tools listlengths 0 9 | messages listlengths 2 39 |
|---|---|---|---|---|---|
grug-v3-smith-tool-8045u::stripped | smith_tool | think | true | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks."
},
{
"role": "user",
"content": "<uploaded_files>\n/testbed\n</uploaded_files>\nI've uploaded a python code repository in the directory /testbed. Consider the following PR description:\... |
fresh-code-44795 | fresh_code | full | false | [] | [
{
"role": "system",
"content": "You are a precise, knowledgeable assistant. Be direct and accurate."
},
{
"role": "user",
"content": "Create a Python function that accepts two multi-dimensional arrays as input and returns a new list with the element-wise product of the input lists. The function ... |
fresh-gsm-3050 | fresh_math | full | false | [] | [
{
"role": "system",
"content": "You are a coding assistant running inside a developer tool."
},
{
"role": "user",
"content": "Janet bought some muffins at the bakery. Each muffin is 75 cents. Janet paid $20 and got $11 in change back. How many muffins did Janet buy?"
},
{
"role": "assist... |
grug-v3-nebius-41245t | nebius | think | false | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "SETTING: You are an autonomous programmer, and you're working directly in the command line with a special interface.\n\nThe special interface consists of a file editor that shows you 100 lines of a file at a time.\nIn addition to typical bash commands, you can also use the fo... |
fresh-chat-7518 | fresh_chat | full | false | [] | [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Based on the paragraph below, which are the most and least popular National Parks in the US?\n\nThe United States has 63 national parks, which are congressionally designated protected areas operated by... |
fresh-code-25345 | fresh_code | full | false | [] | [
{
"role": "system",
"content": "You are a coding assistant running inside a developer tool."
},
{
"role": "user",
"content": "Generate correct SQL queries that not only check if a record exists with a given condition, but also manage and implement additional relational database operations. For t... |
grug-v3-toolace-6974 | toolace | think | false | [
{
"type": "function",
"function": {
"name": "media_content.schedule_review",
"description": "Schedule a review for a media content.",
"parameters": {
"type": "object",
"properties": {
"content_id": {
"type": "string",
"description": "The un... | [
{
"role": "system",
"content": "You are a helpful assistant with access to tools. Use them when needed."
},
{
"role": "user",
"content": "I need to schedule a review for my media content and check if it's compliant with regulations. The content ID is ‘content123’. I want to schedule the review f... |
fresh-gsm-4962 | fresh_math | full | false | [] | [
{
"role": "system",
"content": "You are a precise, knowledgeable assistant. Be direct and accurate."
},
{
"role": "user",
"content": "Kendra wants enough shirts that she only has to do laundry once every two weeks. She wears one shirt to school for each of the five weekdays. Three days a week, s... |
fresh-id-116 | fresh_identity | full | false | [] | [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Who made you?"
},
{
"role": "assistant",
"content": "<think>Identity question. State creator ProCreations, base Ornith 1.0 35B, not big labs.</think>\n\nI’m Grug 35B v2, created by ProCreat... |
grug-v3-smith-ticks-1284 | smith_ticks | think | false | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "You are a software engineering agent working in a repo checkout. Use the bash tool to explore, edit and test until the task is solved."
},
{
"role": "user",
"content": "<uploaded_files>\n/testbed\n</uploaded_files>\nI've uploaded a python code repository in the di... |
grug-v3-nebius-70720t | nebius | think | false | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "SETTING: You are an autonomous programmer, and you're working directly in the command line with a special interface.\n\nThe special interface consists of a file editor that shows you 100 lines of a file at a time.\nIn addition to typical bash commands, you can also use the fo... |
grug-v3-nebius-54059t::stripped | nebius | think | true | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "SETTING: You are an autonomous programmer, and you're working directly in the command line with a special interface.\n\nThe special interface consists of a file editor that shows you 100 lines of a file at a time.\nIn addition to typical bash commands, you can also use the fo... |
fresh-chat-2964 | fresh_chat | full | false | [] | [
{
"role": "user",
"content": "Which country has won the most world cups in soccer?"
},
{
"role": "assistant",
"content": "<think>FIFA men's World Cup most titles: Brazil, 5. Ambiguous soccer World Cups, but standard meaning men's tournament.</think>\n\nBrazil has won the most FIFA World Cups in ... |
grug-v3-nebius-4670t::stripped | nebius | think | true | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "SETTING: You are an autonomous programmer, and you're working directly in the command line with a special interface.\n\nThe special interface consists of a file editor that shows you 100 lines of a file at a time.\nIn addition to typical bash commands, you can also use the fo... |
grug-v3-nebius-197 | nebius | think | false | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "SETTING: You are an autonomous programmer, and you're working directly in the command line with a special interface.\n\nThe special interface consists of a file editor that shows you 100 lines of a file at a time.\nIn addition to typical bash commands, you can also use the fo... |
grug-v3-hermes-glaive-function-calling-5k-2912::stripped | hermes | think | true | [
{
"type": "function",
"function": {
"name": "search_restaurants",
"description": "Search for restaurants based on location and cuisine",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The l... | [
{
"role": "system",
"content": "You are a function-calling AI. Use the provided tools when needed."
},
{
"role": "user",
"content": "I'm in New York and I'm craving for some Italian food. Can you suggest some restaurants?"
},
{
"role": "assistant",
"content": "",
"tool_calls": [
... |
grug-v3-smith-tool-9908 | smith_tool | think | false | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks.\n<IMPORTANT>\n* If user provides a path, you should NOT assume it's relative to the current working directory. Instead, you should explore the file system to find the file before working on it.\n</I... |
fresh-code-38170 | fresh_code | full | false | [] | [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "In Python, write a function that takes a pair of sentences and determines if they are palindromes of each other when punctuations, spaces, and case sensitivity are not considered."
},
{
"role":... |
grug-v3-glaive-55861 | glaive | think | false | [
{
"type": "function",
"function": {
"name": "generate_password",
"description": "Generate a random password",
"parameters": {
"type": "object",
"properties": {
"length": {
"type": "integer",
"description": "The length of the password"
... | [
{
"role": "system",
"content": "You are a helpful assistant with access to tools. Use them when needed."
},
{
"role": "user",
"content": "Hi, I need a new password. Can you generate one for me?"
},
{
"role": "assistant",
"content": "<think>Need password. generate_password requires le... |
grug-v3-smith-tool-8923u | smith_tool | think | false | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "You are a helpful assistant that can interact with a computer to solve tasks."
},
{
"role": "user",
"content": "<uploaded_files>\n/testbed\n</uploaded_files>\nI've uploaded a python code repository in the directory /testbed. Consider the following PR description:\... |
fresh-code-57201 | fresh_code | full | false | [] | [
{
"role": "user",
"content": "Draft a SQL command to not only identify and retrieve the data entries whose specific attribute within a table records a particular value, but also sort the data in descending order and limit the data entries to a certain number.\ntable: transactions\nattribute: amount\nspecifi... |
fresh-code-67215 | fresh_code | full | false | [] | [
{
"role": "system",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "I need to do an analysis plan, for my psychology research and do not know where to look on how to do one. I just know my supervisors want one. We are looking into future thinking and the impact on tho... |
fresh-num-2057 | fresh_math | full | false | [] | [
{
"role": "system",
"content": "You are a precise, knowledgeable assistant. Be direct and accurate."
},
{
"role": "user",
"content": "Find the coordinates of the center of the hyperbola \\[\\frac{(3y+3)^2}{7^2} - \\frac{(4x-8)^2}{6^2} = 1.\\]"
},
{
"role": "assistant",
"content": "<t... |
fresh-ag-294 | fresh_agentic | full | false | [
{
"type": "function",
"function": {
"name": "search_flights",
"description": "Search flights",
"parameters": {
"type": "object",
"properties": {
"from_airport": {
"type": "string"
},
"to_airport": {
"type": "string"
... | [
{
"role": "system",
"content": "You are a precise, knowledgeable assistant. Be direct and accurate."
},
{
"role": "user",
"content": "Please book me a hotel room in Lisbon for 3 nights."
},
{
"role": "assistant",
"content": "<think>book_hotel requires city, checkin, nights. Given cit... |
grug-v3-hermes-func-calling-singleturn-175 | hermes | think | false | [
{
"type": "function",
"function": {
"name": "initiate_crypto_purchase",
"description": "Initiates a cryptocurrency purchase on the user's Coinbase account.",
"parameters": {
"type": "object",
"properties": {
"coinbase_account_id": {
"type": "string",
... | [
{
"role": "system",
"content": "You are a function-calling AI. Use the provided tools when needed."
},
{
"role": "user",
"content": "I would like to initiate a purchase of Bitcoin using my Coinbase account. For this transaction, I'd like to use my credit card as the payment method. Specifically,... |
fresh-num-7497 | fresh_math | full | false | [] | [
{
"role": "system",
"content": "You are a helpful AI assistant."
},
{
"role": "user",
"content": "I am going to put 6 posters with a width of 30 centimeters (cm) in a row on a wall with a width of 3 meters (m) and 20 centimeters (cm). Determine how many centimeters (cm) the distance must be to e... |
fresh-chat-5205 | fresh_chat | full | false | [] | [
{
"role": "user",
"content": "Please give me the list of airports that are owned by Australia Pacific Airports Corporation.\n\nAustralia Pacific Airports Corporation Limited (APAC) is an unlisted company and owner of two Australian airports: Melbourne Airport and Launceston Airport. Each airport is operated... |
fresh-code-52538 | fresh_code | full | false | [] | [
{
"role": "system",
"content": "You are an expert programmer. Help the user with their tasks."
},
{
"role": "user",
"content": "Construct a Python function that scrutinizes a supplied tuple for the presence of any None values, blank strings, or zero values. Upon detection of a None value, blank ... |
grug-v3-smith-ticks-16057 | smith_ticks | think | false | [
{
"type": "function",
"function": {
"name": "bash",
"description": "Run a bash command in the repo environment.",
"parameters": {
"type": "object",
"properties": {
"command": {
"type": "string",
"description": "Bash command to execute"
... | [
{
"role": "system",
"content": "You are a software engineering agent working in a repo checkout. Use the bash tool to explore, edit and test until the task is solved."
},
{
"role": "user",
"content": "<uploaded_files>\n/testbed\n</uploaded_files>\nI've uploaded a python code repository in the di... |
End of preview. Expand in Data Studio
grug-35b-v2-train
brain food that make grug-35b-v2. 7,106 row, ~14.5M context token, ~2.5M trained token.
what in box
| slice | rows | loss | what |
|---|---|---|---|
| SWE agent trajectory (nebius/smith) | 2,271 | think-only | real agentic coding, grug think, tool call trained, old say-word context only |
| API tool convo (toolace/glaive/hermes) | 935 | think-only | multi-turn tool use |
| fresh code (gpt-5.5) | 1,398 | full | hard code task, design think, clean answer |
| fresh math (gpt-5.5) | 1,007 | full | gsm8k + numina problem, full derivation in grug think |
| fresh chat (gpt-5.5) | 894 | full | dolly-style instruction, normal english answer |
| fresh agentic (gpt-5.5) | 481 | full | synthetic tool session, error recovery, clarify case |
| fresh identity (gpt-5.5) | 120 | full | who-are-you set (Grug 35B v2 + Ornith facts) |
trajectory slice come from grug-think-v3-10k (DeepSeek-V4-Pro rewrite, 100% technical anchor kept). fresh slice made by gpt-5.5 with strict grug-dialect gate (banned planner-English regex, schema check, python ast gate, math answer check).
special sauce
loss_mode: "think" row train only<think>+ tool call + im_end (old seed english never imitated). "full" row train whole assistant body.train_last_only+ stripped-history variants (502 row): history think REMOVED, only final turn trained. this teach model the world agent framework actually replay (OpenCode strip old think). 35b brother die from not knowing this world. 27b not die.- query-boundary variants for multi-query convo.
- every row verified >= 25 labeled token under real tokenizer at 6144 cap.
shape
{"id": "...", "source": "...", "loss_mode": "think|full",
"train_last_only": false, "tools": [...],
"messages": [{"role": "...", "content": "<think>grug brain</think>\n\nsay", "tool_calls": [...]}]}
grug made by ProCreations.
- Downloads last month
- 20
