Instructions to use theophilusowiti/Caracal_AfroLlama_int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use theophilusowiti/Caracal_AfroLlama_int4 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Jacaranda/AfroLlama_V1")
model = PeftModel.from_pretrained(base_model, "theophilusowiti/Caracal_AfroLlama_int4")

Transformers

How to use theophilusowiti/Caracal_AfroLlama_int4 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="theophilusowiti/Caracal_AfroLlama_int4")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("theophilusowiti/Caracal_AfroLlama_int4", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use theophilusowiti/Caracal_AfroLlama_int4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "theophilusowiti/Caracal_AfroLlama_int4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theophilusowiti/Caracal_AfroLlama_int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/theophilusowiti/Caracal_AfroLlama_int4

SGLang

How to use theophilusowiti/Caracal_AfroLlama_int4 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "theophilusowiti/Caracal_AfroLlama_int4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theophilusowiti/Caracal_AfroLlama_int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "theophilusowiti/Caracal_AfroLlama_int4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "theophilusowiti/Caracal_AfroLlama_int4",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use theophilusowiti/Caracal_AfroLlama_int4 with Docker Model Runner:
```
docker model run hf.co/theophilusowiti/Caracal_AfroLlama_int4
```

theophilusowiti commited on Jun 3

Commit

0b44a6e

verified ·

1 Parent(s): 57114bf

End of training

Browse files

Files changed (1) hide show

README.md +65 -0

README.md ADDED Viewed

	@@ -0,0 +1,65 @@

+---
+library_name: peft
+base_model: Jacaranda/AfroLlama_V1
+tags:
+- base_model:adapter:Jacaranda/AfroLlama_V1
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: Caracal_AfroLlama_int4
+  results: []
+---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# Caracal_AfroLlama_int4
+This model is a fine-tuned version of [Jacaranda/AfroLlama_V1](https://huggingface.co/Jacaranda/AfroLlama_V1) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8681
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.03
+- num_epochs: 2
+### Training results
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 1.8109        | 1.0   | 17746 | 1.9012          |
+| 1.7053        | 2.0   | 35492 | 1.8681          |
+### Framework versions
+- PEFT 0.19.1
+- Transformers 5.5.1
+- Pytorch 2.12.0+cu126
+- Datasets 4.8.5
+- Tokenizers 0.22.2