bartowski/ProCreations_grug-35b-GGUF
Image-Text-to-Text • 35B • Updated • 3.34k • 4
Datasets:
id stringlengths 16 46 | source stringclasses 6
values | tools listlengths 0 9 | messages listlengths 3 71 |
|---|---|---|---|
grug-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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-v2-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 movie details for Inception. get_movie_details requir... |
grug-v2-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-v2-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-v2-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-v2-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-v2-10k
grug make second brain box. first box teach short. second box teach dense.
short not whole goal. useful thought per token goal. hard bug need evidence, branch, exact path, risk, verify plan. grug keep all. grug throw grammar padding in fire.
what in box
- exactly 10,000 full agent trajectory
- 62,722 assistant think turn rewritten by DeepSeek-V4-Pro
- human say-word unchanged
- system/user/tool observation unchanged
- tool call and arguments unchanged byte-for-byte after JSON parse
- 10,000 trajectory pass immutable-field check
- dataset private for ProCreations
source mix:
- glaive: 1,000
- hermes: 1,000
- nebius: 2,200
- smith_ticks: 2,100
- smith_tool: 2,200
- toolace: 1,500
coding cave get bigger share on purpose. simple API call still present. model must know when poke tool, when ask missing value, when answer direct.
grug dialect measured
| measure | old trace | new trace |
|---|---|---|
| think word mean | 13.12 | 16.75 |
| think word median | 12 | 13 |
| think word p90 | 21 | 30 |
| function-word ratio | 13.5% | 12.2% |
| forbidden filler trace | 6811 | 0 |
| technical anchor coverage | 60.9% | 57.9% |
new mean may grow some. good. complex trace need real meat. p99 = 67 word; max = 261. simple call stay tiny. long trace earned by real constraint, not "Let me carefully think" smoke.
whole trajectory brain: mean 105.05 word, p90 205, p99 328, max 666. complex task get many connected terse turn, not one mysterious tiny thought.
45.53% trace stayed exact because old trace already pass density + meaning test. grug no rewrite good club merely to make dataset look busy.
grug no dumb stop-word knife. "to" or "has" stay when exact meaning need. gone when grammar decoration only.
shape
same schema as grug-think:
{"id":"grug-v2-...","source":"smith_tool","tools":[...],"messages":[...]}
assistant brain first:
<think>Build fails: missing free_threading_config.pxi. reinstall no fix. Editable install next; if same failure, inspect warning branch statically and record test constraint.</think>
human answer and tool call after brain remain original.
how grug make
- deterministic sample from original training split; current RL and held-out IDs excluded
- DeepSeek-V4-Pro see chronological trajectory and target action
- model emit JSON list of replacement brain turn only
- strict repair loop reject prose-heavy, filler, first-person, malformed, missing turn
- rank valid candidate by low grammar padding + exact technical anchor coverage
- choose source quotas, exactly 10k
- rebuild each row from original sacred fields; replace
<think>only - validate all immutable fields, hash final JSONL
builder prompt, validator, quotas, and release selection live in scripts/build_grug_think_v2.py. 100 old/new audit pair live in audit/. final SHA-256: 3a245cb23266b52a15b995b5695bf4e2d340283e2f97bef2b2e06fc69c4fcc92.
grug honest: synthetic reasoning reconstructed around known successful action. not raw hidden brain from original agent. evaluator must still test model in real loop. dataset alone no magic club.
- Downloads last month
- 109
