Instructions to use afrideva/TinyLlama-3T-1.1bee-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use afrideva/TinyLlama-3T-1.1bee-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="afrideva/TinyLlama-3T-1.1bee-GGUF",
	filename="tinyllama-3t-1.1bee.fp16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use afrideva/TinyLlama-3T-1.1bee-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M

Use Docker

docker model run hf.co/afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use afrideva/TinyLlama-3T-1.1bee-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "afrideva/TinyLlama-3T-1.1bee-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "afrideva/TinyLlama-3T-1.1bee-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M

Ollama
How to use afrideva/TinyLlama-3T-1.1bee-GGUF with Ollama:
```
ollama run hf.co/afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M
```

Unsloth Studio

How to use afrideva/TinyLlama-3T-1.1bee-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/TinyLlama-3T-1.1bee-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for afrideva/TinyLlama-3T-1.1bee-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for afrideva/TinyLlama-3T-1.1bee-GGUF to start chatting

Docker Model Runner
How to use afrideva/TinyLlama-3T-1.1bee-GGUF with Docker Model Runner:
```
docker model run hf.co/afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M
```

Lemonade

How to use afrideva/TinyLlama-3T-1.1bee-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull afrideva/TinyLlama-3T-1.1bee-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.TinyLlama-3T-1.1bee-GGUF-Q4_K_M

List all available models

lemonade list

BEE-spoke-data/TinyLlama-3T-1.1bee-GGUF

Quantized GGUF model files for TinyLlama-3T-1.1bee from BEE-spoke-data

Name	Quant method	Size
tinyllama-3t-1.1bee.fp16.gguf	fp16	2.20 GB
tinyllama-3t-1.1bee.q2_k.gguf	q2_k	432.13 MB
tinyllama-3t-1.1bee.q3_k_m.gguf	q3_k_m	548.40 MB
tinyllama-3t-1.1bee.q4_k_m.gguf	q4_k_m	667.81 MB
tinyllama-3t-1.1bee.q5_k_m.gguf	q5_k_m	782.04 MB
tinyllama-3t-1.1bee.q6_k.gguf	q6_k	903.41 MB
tinyllama-3t-1.1bee.q8_0.gguf	q8_0	1.17 GB

Original Model Card:

TinyLlama-3T-1.1bee

A grand successor to the original. This one has the following improvements:

start from finished 3T TinyLlama
vastly improved and expanded SoTA beekeeping dataset

Model description

This model is a fine-tuned version of TinyLlama-1.1b-3T on the BEE-spoke-data/bees-internal dataset.

It achieves the following results on the evaluation set:

Loss: 2.1640
Accuracy: 0.5406

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 2
seed: 13707
gradient_accumulation_steps: 16
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.4432	0.19	50	2.3850	0.5033
2.3655	0.39	100	2.3124	0.5129
2.374	0.58	150	2.2588	0.5215
2.3558	0.78	200	2.2132	0.5291
2.2677	0.97	250	2.1828	0.5348
2.0701	1.17	300	2.1788	0.5373
2.0766	1.36	350	2.1673	0.5398
2.0669	1.56	400	2.1651	0.5402
2.0314	1.75	450	2.1641	0.5406
2.0281	1.95	500	2.1639	0.5407

Framework versions

Transformers 4.36.2
Pytorch 2.1.0
Datasets 2.16.1
Tokenizers 0.15.0

Downloads last month: 234

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

View +1 variant

Model tree for afrideva/TinyLlama-3T-1.1bee-GGUF

Base model

TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T

Finetuned

BEE-spoke-data/TinyLlama-3T-1.1bee

Quantized

(1)

this model

afrideva
/

TinyLlama-3T-1.1bee-GGUF