pdesj/Llama-3.2-1B-nba-ner-GGUF

pdesj/ Llama-3.2-1B-nba-ner-GGUF

19 Downloads Updated 7 months ago

Fine-tuned version of Llama 3.1 1B, optimized for NER tasks on NBA sentences containing player and team names.

tools

ollama run pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M

OpenCode

OpenCode ollama launch opencode --model pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M

Hermes Agent

Hermes Agent ollama launch hermes --model pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M

OpenClaw

OpenClaw ollama launch openclaw --model pdesj/Llama-3.2-1B-nba-ner-GGUF:Q4_K_M

Models

Name

1 model

Size / Usage

Context

Input

Llama-3.2-1B-nba-ner-GGUF:Q4_K_M

808MB · 128K context window · Text · 7 months ago

Llama-3.2-1B-nba-ner-GGUF:Q4_K_M

808MB

128K

Text

Readme

This model is a fine-tuned version of Llama 3.1 1B, optimized for Named Entity Recognition (NER) tasks on NBA sentences. It is specifically designed to extract player and team names from text.

Performances

The model is designed for efficiency: it matches performances of state-of-the-art models 10x larger, while maintaining fast inference times.

Model Comparison

Model	Size (B)	Accuracy (%)	Mean Processing Duration* (s)
Llama-3.2-nba-ner	1	90.1	0.38
Llama3.2	1	32.7	0.79
Gemma2	2	58.3	1.43
Gemma3	4	75.3	0.69
Llama3.1	8	56.5	1.16
Gemma3	12	92.9	2.73

* Benchmarked on an RTX 3060 Laptop GPU using the test part of the pdesj/nba-ner-team-player-1617 dataset.

Dataset

The model was trained using the train part of the pdesj/nba-ner-team-player-1617 dataset. This dataset contains annotated NBA related sentences in english and french, with labeled player and team names, synthetically generated using LLMs, and reviewed by a human annotator.

References

Codebase used to train the model: repo
Trained with unsloth

This model is a fine-tuned version of `Llama 3.1 1B`, optimized for Named Entity Recognition (NER) tasks on NBA sentences. It is specifically designed to extract player and team names from text.

## Performances

The model is designed for efficiency: it matches performances of state-of-the-art models **10x larger**, while maintaining fast inference times.

![ner_accuracy_evaluation_results](https://cdn-uploads.huggingface.co/production/uploads/66a403a107dd6d0ab45a9a1b/J_PUlnQmWaC9wgZ4zYVaW.png)

**Model Comparison**

| Model                | Size (B) | Accuracy (%) | Mean Processing Duration* (s) |
|----------------------|----------|--------------|-------------------------------|
| Llama-3.2-nba-ner    | 1        | 90.1         | 0.38                          |
| Llama3.2             | 1        | 32.7         | 0.79                          |
| Gemma2               | 2        | 58.3         | 1.43                          |
| Gemma3               | 4        | 75.3         | 0.69                          |
| Llama3.1             | 8        | 56.5         | 1.16                          |
| Gemma3               | 12       | 92.9         | 2.73                          |

\* *Benchmarked on an RTX 3060 Laptop GPU using the test part of the [pdesj/nba-ner-team-player-1617](https://huggingface.co/datasets/pdesj/nba-ner-team-player-1617) dataset.*

## Dataset

The model was trained using the train part of the [pdesj/nba-ner-team-player-1617](https://huggingface.co/datasets/pdesj/nba-ner-team-player-1617) dataset. This dataset contains annotated NBA related sentences in english and french, with labeled player and team names, synthetically generated using LLMs, and reviewed by a human annotator.

## References

- Codebase used to train the model: [repo](https://github.com/pdgarden/ner-llm-finetuning)
- Trained with [unsloth](https://unsloth.ai/)

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)