Instructions to use injazsmart/thoth_text_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use injazsmart/thoth_text_v3 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = PeftModel.from_pretrained(base_model, "injazsmart/thoth_text_v3")

Transformers

How to use injazsmart/thoth_text_v3 with Transformers:

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

pipe = pipeline("text-generation", model="injazsmart/thoth_text_v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("injazsmart/thoth_text_v3")
model = AutoModelForCausalLM.from_pretrained("injazsmart/thoth_text_v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use injazsmart/thoth_text_v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "injazsmart/thoth_text_v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "injazsmart/thoth_text_v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/injazsmart/thoth_text_v3

SGLang

How to use injazsmart/thoth_text_v3 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 "injazsmart/thoth_text_v3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "injazsmart/thoth_text_v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "injazsmart/thoth_text_v3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "injazsmart/thoth_text_v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use injazsmart/thoth_text_v3 with Docker Model Runner:
```
docker model run hf.co/injazsmart/thoth_text_v3
```

🧠 Thoth Text v3

نموذج Thoth Text v3 هو إصدار مطوّر من Qwen/Qwen2.5-7B-Instruct، تم تدريبه باستخدام أسلوب LoRA fine-tuning عبر مكتبة Axolotl، على بيانات نصية عربية تم إعدادها محليًا (غير منشورة).

📋 معلومات أساسية

Base model: Qwen/Qwen2.5-7B-Instruct
Previous adapters:
- injazsmart/thoth_text
- injazsmart/thoth_text_v2
Current version: thoth_text_v3
Framework: Axolotl + PEFT + Transformers
Hardware: 8-bit training على GPU واحد

⚙️ إعدادات التدريب (config.yaml)

adapter: lora
base_model: Qwen/Qwen2.5-7B-Instruct
bf16: auto

lora_model_dir: injazsmart/thoth_text_v2

datasets:
  - path: ./data/injaz.json
    type: alpaca

sequence_len: 4096
micro_batch_size: 16
gradient_accumulation_steps: 1
num_epochs: 2
learning_rate: 0.0001
optimizer: adamw_bnb_8bit

load_in_8bit: true
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
  - q_proj
  - v_proj
  - k_proj
  - o_proj
  - gate_proj
  - down_proj
  - up_proj

train_on_inputs: false
output_dir: ./outputs/thoth_text_v3

Downloads last month: -

Model tree for injazsmart/thoth_text_v3

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Adapter

(2103)

this model