ProCreations/grug-v2-9b
Text Generation • 9B • Updated • 1.1k • 1
Datasets:
id stringlengths 16 46 | source stringclasses 6
values | tools listlengths 0 9 | messages listlengths 3 71 |
|---|---|---|---|
grug-v3-toolace-9439 | toolace | [
{
"type": "function",
"function": {
"name": "JavaValidator.isEmailValid",
"description": "This tool validates if the provided email address is in the correct format according to the standard email format.",
"parameters": {
"type": "object",
"properties": {
"email"... | [
{
"role": "system",
"content": "You are a helpful assistant with access to tools. Use them when needed."
},
{
"role": "user",
"content": "Can you check if the date '2022-07-15' is in the correct format?"
},
{
"role": "assistant",
"content": "<think>Validate date '2022-07-15'. JavaVal... |
grug-v3-glaive-5798 | glaive | [
{
"type": "function",
"function": {
"name": "generate_password",
"description": "Generate a random password",
"parameters": {
"type": "object",
"properties": {
"length": {
"type": "integer",
"description": "The desired length of the passwor... | [
{
"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 for my account. Can you generate one for me?"
},
{
"role": "assistant",
"content": "<think>Need password length, numbers... |
grug-v3-smith-ticks-9779 | smith_ticks | [
{
"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-56488t | nebius | [
{
"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-620 | hermes | [
{
"type": "function",
"function": {
"name": "get_stock_price",
"description": "Get the current stock price",
"parameters": {
"type": "object",
"properties": {
"symbol": {
"type": "string",
"description": "The stock symbol"
}
... | [
{
"role": "system",
"content": "You are a function-calling AI. Use the provided tools when needed."
},
{
"role": "user",
"content": "Can you tell me the current stock price for Apple?"
},
{
"role": "assistant",
"content": "<think>Need Apple stock price. Symbol AAPL. Call get_stock_pr... |
grug-v3-smith-ticks-4046 | smith_ticks | [
{
"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-54899t | nebius | [
{
"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-toolace-9 | toolace | [
{
"type": "function",
"function": {
"name": "Retrieve_Quotes_by_Tag",
"description": "Retrieve a list of quotes by a given tag from the Social domain.",
"parameters": {
"type": "object",
"properties": {
"tag": {
"description": "The tag to search for qu... | [
{
"role": "system",
"content": "You are a helpful assistant with access to tools. Use them when needed."
},
{
"role": "user",
"content": "Could you help me find some trending hashtags on TikTok right now?"
},
{
"role": "assistant",
"content": "<think>Need trending hashtags. Hashtag_I... |
grug-v3-hermes-glaive-function-calling-5k-920 | hermes | [
{
"type": "function",
"function": {
"name": "get_movie_details",
"description": "Get details of a movie",
"parameters": {
"type": "object",
"properties": {
"title": {
"type": "string",
"description": "The title of the movie"
}
... | [
{
"role": "system",
"content": "You are a function-calling AI. Use the provided tools when needed."
},
{
"role": "user",
"content": "Can you tell me about the movie \"Inception\"?"
},
{
"role": "assistant",
"content": "<think>Need Inception details. get_movie_details needs title. Cal... |
grug-v3-smith-ticks-664 | smith_ticks | [
{
"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-toolace-10384 | toolace | [
{
"type": "function",
"function": {
"name": "Get_Sailors",
"description": "Get list of all **Lost Ark** sailors details",
"parameters": {
"type": "object",
"properties": {
"server": {
"description": "The server to query",
"type": "string"
... | [
{
"role": "system",
"content": "You are a helpful assistant with access to tools. Use them when needed."
},
{
"role": "user",
"content": "Could you please fetch the upcoming CSGO matches and tournaments for the first page, with a limit of 5 results per page, get the champion tier list for 'plati... |
grug-v3-smith-tool-1243u | smith_tool | [
{
"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:\... |
grug-v3-hermes-glaive-function-calling-5k-2789 | hermes | [
{
"type": "function",
"function": {
"name": "calculate_distance",
"description": "Calculate the distance between two locations",
"parameters": {
"type": "object",
"properties": {
"origin": {
"type": "string",
"description": "The origin loca... | [
{
"role": "system",
"content": "You are a function-calling AI. Use the provided tools when needed."
},
{
"role": "user",
"content": "Hi, I need to know the distance between New York and Los Angeles. I plan to drive."
},
{
"role": "assistant",
"content": "<think>Need distance New York... |
End of preview. Expand in Data Studio
grug-think-v3-10k
v2 brain short. v2 brain useful. but some v2 brain wear office shirt.
"User wants hello world Python. Provide code." short English, yes. grug, no. v3 tear off office shirt. keep brain meat.
old: User wants hello world Python. Simple code snippet, no tools needed. Provide code and brief explanation.
new: Need Python hello-world. Tiny snippet. No tool. Give code, brief explain.
complex cave different. grug no crush branch into pebble. exact path, error, hypothesis, risk, competing branch, verification stay. grammar padding burn.
what in box
- exactly 10,000 full agent trajectory
- exactly 62,722 assistant brain turn
- 11,889 trace changed; 50,833 already-strong trace kept exact
- human say-word unchanged
- system/user/tool observation unchanged
- tool call + argument unchanged
- 146,785/146,785 exact technical anchor retained
- 10,000 trajectory pass immutable-field check
source mix:
- glaive: 1,000
- hermes: 1,000
- nebius: 2,200
- smith_ticks: 2,100
- smith_tool: 2,200
- toolace: 1,500
dialect number
| measure | v2 trace | v3 trace |
|---|---|---|
| function-word ratio | 12.2% | 11.2% |
| matched planner-English pattern | 1,392 | 0 |
| word mean | 16.65 | 16.6 |
| new word median | — | 13 |
| new p90 / p99 / max | — | 30 / 67 / 275 |
| hard-anchor retention | — | 100.0% |
| semantic-term retention mean | — | 98.1% |
grug no blind stop-word knife. to, has, with may stay when technical
meaning need. planner frame fail. exact code/path/number sacred.
shape
same OpenAI conversation shape as grug-think-v2-10k:
{"id":"grug-v3-...","source":"smith_tool","tools":[...],"messages":[...]}
assistant brain first:
<think>Tuple binding likely mirror List. Inspect inner-field ownership, parent/name propagation. Patch narrow override. Add nested Tuple regression test. Run targeted suite.</think>
human answer and tool action after brain stay original.
how grug make
- start exact public v2 10k rows
- DeepSeek-V4-Pro see chronological prefix + target action
- rewrite private brain only; already-strong fragment may stay exact
- deterministic safe normalization remove known scaffolds (
User thanks,need to,answer with) without touching technical anchors - reject remaining planner frame, first person, grammar-heavy trace
- reject missing path, symbol, command, number, long reasoning branch
- retry weak row; resume by trajectory id
- rebuild from original row, replace
<think>only; assert every sacred field, hash final JSONL
builder + validators live in scripts/. 300 old/new trajectory audit live in
audit/. final SHA-256: 883bfc8b48e89e80005cc7e12c844774bf9887794d05cd36f611f0391cd0eaf7.
grug honest: thought synthetic reconstruction around known action. not secret raw brain. real agent benchmark still judge model. dataset no magic club.
- Downloads last month
- 71