Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
35.6
TFLOPS
Nick Perez
nkpz
6
52
Follow
Mjsky's profile picture
Mykee's profile picture
KnutJaegersberg's profile picture
41 followers
·
10 following
AI & ML interests
Open source LLM stuff.
Recent Activity
liked
a model
1 day ago
Sourajit123/SouraTTS
reacted
to
codelion
's
post
with ❤️
about 1 year ago
I recently worked on a LoRA that improves tool use in LLM. Thought the approach might interest folks here. The issue I have had when trying to use some of the local LLMs with coding agents is this: Me: "Find all API endpoints with authentication in this codebase" LLM: "You should look for @app.route decorators and check if they have auth middleware..." But I often want it to search the files and show me but the LLM doesn't trigger a tool use call. To fine-tune it for tool use I combined two data sources: 1. Magpie scenarios - 5000+ diverse tasks (bug hunting, refactoring, security audits) 2. Real execution - Ran these on actual repos (FastAPI, Django, React) to get authentic tool responses This ensures the model learns both breadth (many scenarios) and depth (real tool behavior). Tools We Taught: - `read_file` - Actually read file contents - `search_files` - Regex/pattern search across codebases - `find_definition` - Locate classes/functions - `analyze_imports` - Dependency tracking - `list_directory` - Explore structure - `run_tests` - Execute test suites Improvements: - Tool calling accuracy: 12% → 80% - Correct parameters: 8% → 87% - Multi-step tasks: 3% → 78% - End-to-end completion: 5% → 80% - Tools per task: 0.2 → 3.8 The LoRA really improves on intential tool call as an example consider the query: "Find ValueError in payment module" The response proceeds as follows: 1. Calls `search_files` with pattern "ValueError" 2. Gets 4 matches across 3 files 3. Calls `read_file` on each match 4. Analyzes context 5. Reports: "Found 3 ValueError instances: payment/processor.py:47 for invalid amount, payment/validator.py:23 for unsupported currency..." Resources: - Colab notebook https://colab.research.google.com/github/codelion/ellora/blob/main/Ellora_Recipe_3_Enhanced_Tool_Calling_and_Code_Understanding.ipynb - Model - https://huggingface.co/codelion/Llama-3.2-1B-Instruct-tool-calling-lora - GitHub - https://github.com/codelion/ellora
liked
a model
over 1 year ago
Edens-Gate/Humanize-Rei-Slerp
View all activity
Organizations
None yet
nkpz
's activity
All
Models
Datasets
Spaces
Buckets
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
1 day ago
Sourajit123/SouraTTS
Text-to-Speech
•
Updated
Mar 16
•
8
liked
4 models
over 1 year ago
Edens-Gate/Humanize-Rei-Slerp
Text Generation
•
12B
•
Updated
Apr 3, 2025
•
23
•
2
Ateron/Glowing-Forest-2-12B
Text Generation
•
12B
•
Updated
Mar 19, 2025
•
24
•
2
suayptalha/Lix-14B-v0.1
Text Generation
•
15B
•
Updated
Mar 7, 2025
•
26
•
9
Xiaojian9992024/Qwen2.5-Dyanka-7B-Preview
Text Generation
•
8B
•
Updated
Feb 26, 2025
•
45
•
•
12
liked
a model
about 2 years ago
nvidia/Mistral-NeMo-Minitron-8B-Base
Text Generation
•
8B
•
Updated
Aug 22, 2024
•
2.16k
•
180
liked
5 models
over 2 years ago
ruslanmv/Medical-Llama3-8B
Text Generation
•
8B
•
Updated
May 15, 2024
•
132
•
106
Undi95/BigL-7B
Text Generation
•
7B
•
Updated
Mar 25, 2024
•
30
•
6
LoneStriker/BoreanGale-70B-2.4bpw-h6-exl2
Text Generation
•
Updated
Mar 15, 2024
•
12
•
1
Yuma42/KangalKhan-RawRuby-7B
Text Generation
•
7B
•
Updated
Jul 29, 2024
•
71
•
6
TeeZee/BigMaid-20B-v1.0-bpw8.0-h8-exl2
Text Generation
•
Updated
Feb 9, 2024
•
13
•
1
liked
9 models
almost 3 years ago
TheBloke/Sydney_Overthinker_13B-GGUF
13B
•
Updated
Dec 8, 2023
•
1.28k
•
2
microsoft/Orca-2-13b
Text Generation
•
Updated
Nov 22, 2023
•
863
•
•
669
KnutJaegersberg/Deacon-34b-4bit
Text Generation
•
Updated
Dec 3, 2023
•
12
•
2
waldie/Yi-34B-GiftedConvo-merged-4bpw-h6-exl2
Text Generation
•
Updated
Nov 8, 2023
•
11
•
2
FPHam/Autolycus-Mistral_7B
Text Generation
•
7B
•
Updated
Nov 13, 2023
•
66
•
•
11
teknium/OpenHermes-2-Mistral-7B
Text Generation
•
Updated
Nov 2, 2023
•
208
•
•
255
dphn/dolphin-2.1-mistral-7b
Text Generation
•
7B
•
Updated
May 20, 2024
•
261
•
260
QuixiAI/samantha-1.2-mistral-7b
Text Generation
•
Updated
Nov 18, 2023
•
54
•
•
36
nvidia/SteerLM-llama2-13B
Updated
Oct 11, 2023
•
122
•
43
Load more