moondream2-batch-processing
ð
8
demo of batch processing with moondream
Ci Splunk PRO
Csplk
AI & ML interests
None yet
Recent Activity
updated
a Space
about 3 hours ago
Csplk/moondream2-batch-processing
upvoted
an
article
about 9 hours ago
Transformers v5: Simple model definitions powering the AI ecosystem
liked
a model
2 days ago
ggml-org/Ministral-3-3B-Reasoning-2512-GGUF
Organizations
updated
a
Space
about 3 hours ago
upvoted
an
article
about 9 hours ago
Article
Transformers v5: Simple model definitions powering the AI ecosystem
- +2
âĒ
223
liked
a
model
2 days ago
upvoted
a
collection
2 days ago
liked
a
Space
3 days ago
liked
a
Space
10 days ago
Very handy
reacted to
Nymbo's
post with ð
10 days ago
Post
4624
ð I've just shipped a major update to the
Nymbo/Tools MCP server: the
Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.
# The Problem
Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window â a 10,000-row spreadsheet? That's all going into context just to sum a column.
# The Solution: One Tool to Rule Them All
Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:
Don't know what tools are available? The agent can discover them at runtime:
The individual direct tool calls are all still there, but they can be disabled if using the
Agent_Terminal, a single "master tool" that cuts token usage by over 90%!Anthropic found 98.7% context savings using code execution with MCP, Cloudflare published similar findings. This is my open-source implementation of the same idea.
# The Problem
Traditional MCP exposes every tool definition directly to the model. With 12 tools, that's thousands of tokens consumed *before the conversation even starts*. Each tool call also passes intermediate results through the context window â a 10,000-row spreadsheet? That's all going into context just to sum a column.
# The Solution: One Tool to Rule Them All
Agent_Terminal wraps all 12 tools (Web_Search, Web_Fetch, File_System, Generate_Image, Generate_Speech, Generate_Video, Deep_Research, Memory_Manager, Obsidian_Vault, Shell_Command, Code_Interpreter) into a single Python code execution gateway.Instead of the model making individual tool calls, it writes Python code that orchestrates the tools directly:
# Search for Bitcoin price
result = Web_Search("current price of bitcoin", max_results=3)
print(result)Don't know what tools are available? The agent can discover them at runtime:
print(search_tools('image')) # Find tools by keyword
print(usage('Generate_Image')) # Get full docs for a specific toolThe individual direct tool calls are all still there, but they can be disabled if using the
Agent_Terminal. Try it now - https://www.nymbo.net/nymbot
-
- 1 reply
liked
2
Spaces
11 days ago
liked
3
models
11 days ago
liked
2
Spaces
12 days ago
liked
a
Space
15 days ago
liked
a
Space
16 days ago
liked
a
model
16 days ago
reacted to
sergiopaniego's
post with ð
16 days ago
Post
2568
we've just added several example scripts to TRL showing how to train models with GRPO using some of the new OpenEnv environments
train a model to interact with a browser (ðŪ BrowserGym Env), play Wordle (ðŪ Wordle Env) and moooore!
TRL (GRPO + vLLM) + OpenEnv! âĄïļ
ð go play with them: https://github.com/huggingface/trl/tree/main/examples/scripts/openenv
ð examples list: https://huggingface.co/docs/trl/main/en/example_overview#scripts
train a model to interact with a browser (ðŪ BrowserGym Env), play Wordle (ðŪ Wordle Env) and moooore!
TRL (GRPO + vLLM) + OpenEnv! âĄïļ
ð go play with them: https://github.com/huggingface/trl/tree/main/examples/scripts/openenv
ð examples list: https://huggingface.co/docs/trl/main/en/example_overview#scripts
liked
a
Space
16 days ago