Applied-Innovation-Center

Karnak-Th-41B-v1.0

README

License: apache-2.0

Model Summary

Table with columns: Property, Details
Property	Details
Model name	Karnak-Th-41B v1.0
Developer	Applied Innovation Center (AIC)
Base model	Qwen/Qwen3.6-35B-A3B
Total parameters	Approximately 41B after depth extension
Architecture	Depth-extended Qwen-based Mixture-of-Experts (MoE) language model
Primary languages	Arabic and English
Response modes	Thinking and non-thinking
Tool integration	OpenAI-compatible function calling through vLLM
Recommended presence penalty	`1.0` for both response modes
Training data	Highly curated and cleaned Arabic, English, and reasoning data
Primary task	Instruction-following text generation
License	Apache 2.0

The parameter count refers to total model parameters, rather than parameters activated per token.

Key Features

Depth extension from 35B to approximately 41B: Additional model layers expand the backbone's capacity, followed by training of the extended model.
Arabic–English training: Bilingual data supports language understanding, generation, and instruction following, with particular attention to Arabic.
Reasoning-focused training: Reasoning examples complement language and instruction data to support tasks requiring analysis and multiple steps.
Hybrid thinking: A single checkpoint supports both intermediate reasoning and direct-response generation.
Tool integration: vLLM serving supports structured function calls for connecting the model to application-defined tools.
Carefully curated data: Training emphasizes data quality through deliberate selection and cleaning of Arabic, English, and reasoning material.
Local deployment: The checkpoint can be hosted on your own infrastructure and adapted to application-specific workflows under its license.

Architecture and Training

Karnak-Th-41B v1.0 starts from the Qwen3.6-35B-A3B backbone and extends its depth to produce an approximately 41B-parameter model. The extended model is then trained on curated bilingual and reasoning data.

The development process can be summarized as:

Qwen3.6-35B-A3B → Depth Extension → Training on Curated Arabic, English, and Reasoning Data → Karnak-Th-41B v1.0

Training focuses on bilingual responses, instruction following, and reasoning behavior across thinking and non-thinking modes.

Thinking and Non-Thinking Modes

Table with columns: Mode, Behavior, Example applications
Mode	Behavior	Example applications
Thinking	Generates intermediate reasoning before the final response.	Multi-step questions, analytical tasks, and problems requiring careful consideration.
Non-thinking	Generates a direct response without an explicit reasoning section.	Conversation, summarization, translation, rewriting, and straightforward questions.

Select the mode through the checkpoint's chat template:

python

enable_thinking=True   # Thinking modeenable_thinking=False  # Non-thinking mode

Use the tokenizer and chat template distributed with this checkpoint, and set enable_thinking to select the response mode. The reasoning parser separates reasoning from the final answer in API responses.

Thinking generally requires more output tokens and can increase latency. Allocate enough generation budget for both reasoning and the final answer.

Usage

The model is loaded from Applied-Innovation-Center/Karnak-Th-41B-v1.0 in the examples below.

1. Hugging Face Transformers

Install a recent Transformers release with support for the checkpoint's Qwen architecture:

bash

pip install -U transformers torch accelerate

Load the checkpoint and generate a response:

python

import torchfrom transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer model_id = "Applied-Innovation-Center/Karnak-Th-41B-v1.0"enable_thinking = True  # Set to False for direct responses. tokenizer = AutoTokenizer.from_pretrained(model_id)config = AutoConfig.from_pretrained(model_id) # Select the loader matching the exported checkpoint configuration.if getattr(config, "vision_config", None) is not None:    from transformers import Qwen3_5MoeForConditionalGeneration    model_class = Qwen3_5MoeForConditionalGenerationelse:    model_class = AutoModelForCausalLM model = model_class.from_pretrained(    model_id,    dtype=torch.bfloat16,    device_map="auto",).eval() messages = [    {"role": "system", "content": "You are a helpful assistant. أجب بلغة المستخدم."},    {"role": "user", "content": "اشرح الفرق بين التعلم الخاضع للإشراف والتعلم المعزز، مع مثال لكل منهما."},] prompt = tokenizer.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True,    enable_thinking=enable_thinking,)inputs = tokenizer(    prompt,    return_tensors="pt",    add_special_tokens=False,).to(model.device) with torch.inference_mode():    outputs = model.generate(        **inputs,        max_new_tokens=4096 if enable_thinking else 1024,        do_sample=True,        temperature=0.6 if enable_thinking else 0.7,        top_p=0.95 if enable_thinking else 0.8,        top_k=20,    ) generated_ids = outputs[0, inputs["input_ids"].shape[1]:]response = tokenizer.decode(generated_ids, skip_special_tokens=True)print(response)

In thinking mode, decoded text may include reasoning delimiters such as <think> and </think>. Keep reasoning and final-answer presentation separate in applications that expose only the final response.

2. vLLM Server

Use a recent vLLM release supporting the exported architecture. Install it in a separate environment from other inference stacks:

bash

pip install -U vllm openai

Start an OpenAI-compatible server with reasoning parsing and automatic tool calling:

bash

vllm serve "Applied-Innovation-Center/Karnak-Th-41B-v1.0" \  --served-model-name karnak-th-41b-v1.0 \  --dtype bfloat16 \  --tensor-parallel-size 2 \  --reasoning-parser qwen3 \  --enable-auto-tool-choice \  --tool-call-parser qwen3_coder \  --port 8000

Adjust --tensor-parallel-size to your GPU topology and available memory.

--reasoning-parser qwen3 separates reasoning from final responses. --enable-auto-tool-choice lets the model select tools supplied in a request, and --tool-call-parser qwen3_coder converts generated function calls into the OpenAI-compatible tool_calls format.

Request Either Response Mode

python

from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") def ask(prompt: str, thinking: bool = True):    response = client.chat.completions.create(        model="karnak-th-41b-v1.0",        messages=[{"role": "user", "content": prompt}],        temperature=0.6 if thinking else 0.7,        top_p=0.95 if thinking else 0.8,        presence_penalty=1.0,        max_tokens=4096 if thinking else 1024,        extra_body={            "top_k": 20,            "chat_template_kwargs": {"enable_thinking": thinking},        },    )    return response.choices[0].message.content # Thinking modeprint(ask("كيف يمكن مقارنة حلين لمشكلة عندما يختلفان في التكلفة والوقت والجودة؟", thinking=True)) # Non-thinking modeprint(ask("اكتب رسالة قصيرة لشكر زميل على مساعدته.", thinking=False))

The server's qwen3 parser can separate reasoning into an additional response field. The example prints the final-answer content field.

Tool Calling

Define tools using JSON schemas and pass them with tool_choice="auto". Your application executes the requested functions and returns their results to the model. The following example completes a tool call using a local multiplication function:

python

import jsonfrom openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") tools = [{    "type": "function",    "function": {        "name": "multiply",        "description": "Multiply two integers and return their product.",        "parameters": {            "type": "object",            "properties": {                "a": {"type": "integer", "description": "The first integer."},                "b": {"type": "integer", "description": "The second integer."},            },            "required": ["a", "b"],            "additionalProperties": False,        },    },}] def multiply(a: int, b: int) -> int:    return a * b functions = {"multiply": multiply}messages = [{"role": "user", "content": "استخدم الأداة لحساب حاصل ضرب 125 في 48."}] def complete(tool_choice):    return client.chat.completions.create(        model="karnak-th-41b-v1.0",        messages=messages,        tools=tools,        tool_choice=tool_choice,        temperature=0.7,        top_p=0.8,        presence_penalty=1.0,        max_tokens=1024,        extra_body={            "top_k": 20,            "chat_template_kwargs": {"enable_thinking": False},        },    ).choices[0].message message = complete("auto")if message.tool_calls:    messages.append(message.model_dump(exclude_none=True))    for call in message.tool_calls:        arguments = json.loads(call.function.arguments)        result = functions[call.function.name](**arguments)        messages.append({            "role": "tool",            "tool_call_id": call.id,            "content": json.dumps({"result": result}),        })    message = complete("none") print(message.content)

Only expose functions your application intends to provide, and validate arguments before executing tools that access external services or modify data.

3. vLLM Offline Inference

Apply the model's chat template before submitting prompts for offline generation:

python

from transformers import AutoTokenizerfrom vllm import LLM, SamplingParams model_id = "Applied-Innovation-Center/Karnak-Th-41B-v1.0"tokenizer = AutoTokenizer.from_pretrained(model_id) llm = LLM(    model=model_id,    dtype="bfloat16",    tensor_parallel_size=2,) messages = [{"role": "user", "content": "Explain reinforcement learning in simple English."}]prompt = tokenizer.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True,    enable_thinking=False,) params = SamplingParams(    temperature=0.7,    top_p=0.8,    top_k=20,    presence_penalty=1.0,    max_tokens=1024,) for output in llm.generate([prompt], params):    print(output.outputs[0].text)

Generation Guidance

We recommend setting presence_penalty=1.0 in both thinking and non-thinking modes when supported by the inference backend. All vLLM generation examples above use this setting.

Adjust temperature, sampling thresholds, and output budgets to your application's requirements.

Explicitly select thinking or non-thinking mode through the chat template.
Give thinking requests sufficient output budget; generation can stop before the final answer if reasoning consumes the token limit.
Use the checkpoint's tokenizer and generation configuration, including its end-of-sequence tokens.
Match serving settings to the checkpoint configuration, available memory, and application workload.

Intended Uses and Limitations

Karnak-Th-41B v1.0 is intended for Arabic–English assistants, question answering, writing, summarization, translation, and reasoning-oriented applications. It can also serve as the generation component of retrieval-augmented systems when supplied with relevant documents.

The model can produce incorrect, incomplete, or biased responses. Thinking mode does not guarantee a correct answer, and generated reasoning should not be treated as evidence of correctness. Retrieved evidence and independent verification remain useful when factual accuracy matters.

License

Karnak-Th-41B v1.0 is released under the Apache License 2.0. See the repository's LICENSE file for the full terms.

Citation

bibtex

@misc{karnak_th_41b_v1_2026,  title        = {Karnak-Th-41B v1.0: A Depth-Extended Arabic-English Language Model with Hybrid Thinking},  author       = {{Applied Innovation Center}},  year         = {2026},  howpublished = {Hugging Face model release},  url          = {https://huggingface.co/Applied-Innovation-Center/Karnak-Th-41B-v1.0}}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Model Details

Model Provider

Applied-Innovation-Center

Model Tree

Base

Qwen/Qwen3.6-35B-A3B

Fine-tuned

this model

Input Modalities

TextImageVideo

Output Modalities

Text

Supported Functionality

Dedicated Endpoints

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Model Summary

Table with columns: Property, Details
Property	Details
Model name	Karnak-Th-41B v1.0
Developer	Applied Innovation Center (AIC)
Base model	Qwen/Qwen3.6-35B-A3B
Total parameters	Approximately 41B after depth extension
Architecture	Depth-extended Qwen-based Mixture-of-Experts (MoE) language model
Primary languages	Arabic and English
Response modes	Thinking and non-thinking
Tool integration	OpenAI-compatible function calling through vLLM
Recommended presence penalty	`1.0` for both response modes
Training data	Highly curated and cleaned Arabic, English, and reasoning data
Primary task	Instruction-following text generation
License	Apache 2.0

The parameter count refers to total model parameters, rather than parameters activated per token.

Key Features

Depth extension from 35B to approximately 41B: Additional model layers expand the backbone's capacity, followed by training of the extended model.
Arabic–English training: Bilingual data supports language understanding, generation, and instruction following, with particular attention to Arabic.
Reasoning-focused training: Reasoning examples complement language and instruction data to support tasks requiring analysis and multiple steps.
Hybrid thinking: A single checkpoint supports both intermediate reasoning and direct-response generation.
Tool integration: vLLM serving supports structured function calls for connecting the model to application-defined tools.
Carefully curated data: Training emphasizes data quality through deliberate selection and cleaning of Arabic, English, and reasoning material.
Local deployment: The checkpoint can be hosted on your own infrastructure and adapted to application-specific workflows under its license.

Architecture and Training

The development process can be summarized as:

Qwen3.6-35B-A3B → Depth Extension → Training on Curated Arabic, English, and Reasoning Data → Karnak-Th-41B v1.0

Training focuses on bilingual responses, instruction following, and reasoning behavior across thinking and non-thinking modes.

Thinking and Non-Thinking Modes

Table with columns: Mode, Behavior, Example applications
Mode	Behavior	Example applications
Thinking	Generates intermediate reasoning before the final response.	Multi-step questions, analytical tasks, and problems requiring careful consideration.
Non-thinking	Generates a direct response without an explicit reasoning section.	Conversation, summarization, translation, rewriting, and straightforward questions.

Select the mode through the checkpoint's chat template:

python

enable_thinking=True   # Thinking modeenable_thinking=False  # Non-thinking mode

enable_thinking=True   # Thinking modeenable_thinking=False  # Non-thinking mode

Thinking generally requires more output tokens and can increase latency. Allocate enough generation budget for both reasoning and the final answer.

Usage

The model is loaded from Applied-Innovation-Center/Karnak-Th-41B-v1.0 in the examples below.

1. Hugging Face Transformers

Install a recent Transformers release with support for the checkpoint's Qwen architecture:

bash

pip install -U transformers torch accelerate

Load the checkpoint and generate a response:

python

import torchfrom transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer model_id = "Applied-Innovation-Center/Karnak-Th-41B-v1.0"enable_thinking = True  # Set to False for direct responses. tokenizer = AutoTokenizer.from_pretrained(model_id)config = AutoConfig.from_pretrained(model_id) # Select the loader matching the exported checkpoint configuration.if getattr(config, "vision_config", None) is not None:    from transformers import Qwen3_5MoeForConditionalGeneration    model_class = Qwen3_5MoeForConditionalGenerationelse:    model_class = AutoModelForCausalLM model = model_class.from_pretrained(    model_id,    dtype=torch.bfloat16,    device_map="auto",).eval() messages = [    {"role": "system", "content": "You are a helpful assistant. أجب بلغة المستخدم."},    {"role": "user", "content": "اشرح الفرق بين التعلم الخاضع للإشراف والتعلم المعزز، مع مثال لكل منهما."},] prompt = tokenizer.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True,    enable_thinking=enable_thinking,)inputs = tokenizer(    prompt,    return_tensors="pt",    add_special_tokens=False,).to(model.device) with torch.inference_mode():    outputs = model.generate(        **inputs,        max_new_tokens=4096 if enable_thinking else 1024,        do_sample=True,        temperature=0.6 if enable_thinking else 0.7,        top_p=0.95 if enable_thinking else 0.8,        top_k=20,    ) generated_ids = outputs[0, inputs["input_ids"].shape[1]:]response = tokenizer.decode(generated_ids, skip_special_tokens=True)print(response)

import torchfrom transformers import AutoConfig, AutoModelForCausalLM, AutoTokenizer model_id = "Applied-Innovation-Center/Karnak-Th-41B-v1.0"enable_thinking = True  # Set to False for direct responses. tokenizer = AutoTokenizer.from_pretrained(model_id)config = AutoConfig.from_pretrained(model_id) # Select the loader matching the exported checkpoint configuration.if getattr(config, "vision_config", None) is not None:    from transformers import Qwen3_5MoeForConditionalGeneration    model_class = Qwen3_5MoeForConditionalGenerationelse:    model_class = AutoModelForCausalLM model = model_class.from_pretrained(    model_id,    dtype=torch.bfloat16,    device_map="auto",).eval() messages = [    {"role": "system", "content": "You are a helpful assistant. أجب بلغة المستخدم."},    {"role": "user", "content": "اشرح الفرق بين التعلم الخاضع للإشراف والتعلم المعزز، مع مثال لكل منهما."},] prompt = tokenizer.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True,    enable_thinking=enable_thinking,)inputs = tokenizer(    prompt,    return_tensors="pt",    add_special_tokens=False,).to(model.device) with torch.inference_mode():    outputs = model.generate(        **inputs,        max_new_tokens=4096 if enable_thinking else 1024,        do_sample=True,        temperature=0.6 if enable_thinking else 0.7,        top_p=0.95 if enable_thinking else 0.8,        top_k=20,    ) generated_ids = outputs[0, inputs["input_ids"].shape[1]:]response = tokenizer.decode(generated_ids, skip_special_tokens=True)print(response)

2. vLLM Server

Use a recent vLLM release supporting the exported architecture. Install it in a separate environment from other inference stacks:

bash

pip install -U vllm openai

Start an OpenAI-compatible server with reasoning parsing and automatic tool calling:

bash

vllm serve "Applied-Innovation-Center/Karnak-Th-41B-v1.0" \  --served-model-name karnak-th-41b-v1.0 \  --dtype bfloat16 \  --tensor-parallel-size 2 \  --reasoning-parser qwen3 \  --enable-auto-tool-choice \  --tool-call-parser qwen3_coder \  --port 8000

vllm serve "Applied-Innovation-Center/Karnak-Th-41B-v1.0" \  --served-model-name karnak-th-41b-v1.0 \  --dtype bfloat16 \  --tensor-parallel-size 2 \  --reasoning-parser qwen3 \  --enable-auto-tool-choice \  --tool-call-parser qwen3_coder \  --port 8000

Adjust --tensor-parallel-size to your GPU topology and available memory.

Request Either Response Mode

python

from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") def ask(prompt: str, thinking: bool = True):    response = client.chat.completions.create(        model="karnak-th-41b-v1.0",        messages=[{"role": "user", "content": prompt}],        temperature=0.6 if thinking else 0.7,        top_p=0.95 if thinking else 0.8,        presence_penalty=1.0,        max_tokens=4096 if thinking else 1024,        extra_body={            "top_k": 20,            "chat_template_kwargs": {"enable_thinking": thinking},        },    )    return response.choices[0].message.content # Thinking modeprint(ask("كيف يمكن مقارنة حلين لمشكلة عندما يختلفان في التكلفة والوقت والجودة؟", thinking=True)) # Non-thinking modeprint(ask("اكتب رسالة قصيرة لشكر زميل على مساعدته.", thinking=False))

from openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") def ask(prompt: str, thinking: bool = True):    response = client.chat.completions.create(        model="karnak-th-41b-v1.0",        messages=[{"role": "user", "content": prompt}],        temperature=0.6 if thinking else 0.7,        top_p=0.95 if thinking else 0.8,        presence_penalty=1.0,        max_tokens=4096 if thinking else 1024,        extra_body={            "top_k": 20,            "chat_template_kwargs": {"enable_thinking": thinking},        },    )    return response.choices[0].message.content # Thinking modeprint(ask("كيف يمكن مقارنة حلين لمشكلة عندما يختلفان في التكلفة والوقت والجودة؟", thinking=True)) # Non-thinking modeprint(ask("اكتب رسالة قصيرة لشكر زميل على مساعدته.", thinking=False))

The server's qwen3 parser can separate reasoning into an additional response field. The example prints the final-answer content field.

Tool Calling

python

import jsonfrom openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") tools = [{    "type": "function",    "function": {        "name": "multiply",        "description": "Multiply two integers and return their product.",        "parameters": {            "type": "object",            "properties": {                "a": {"type": "integer", "description": "The first integer."},                "b": {"type": "integer", "description": "The second integer."},            },            "required": ["a", "b"],            "additionalProperties": False,        },    },}] def multiply(a: int, b: int) -> int:    return a * b functions = {"multiply": multiply}messages = [{"role": "user", "content": "استخدم الأداة لحساب حاصل ضرب 125 في 48."}] def complete(tool_choice):    return client.chat.completions.create(        model="karnak-th-41b-v1.0",        messages=messages,        tools=tools,        tool_choice=tool_choice,        temperature=0.7,        top_p=0.8,        presence_penalty=1.0,        max_tokens=1024,        extra_body={            "top_k": 20,            "chat_template_kwargs": {"enable_thinking": False},        },    ).choices[0].message message = complete("auto")if message.tool_calls:    messages.append(message.model_dump(exclude_none=True))    for call in message.tool_calls:        arguments = json.loads(call.function.arguments)        result = functions[call.function.name](**arguments)        messages.append({            "role": "tool",            "tool_call_id": call.id,            "content": json.dumps({"result": result}),        })    message = complete("none") print(message.content)

import jsonfrom openai import OpenAI client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY") tools = [{    "type": "function",    "function": {        "name": "multiply",        "description": "Multiply two integers and return their product.",        "parameters": {            "type": "object",            "properties": {                "a": {"type": "integer", "description": "The first integer."},                "b": {"type": "integer", "description": "The second integer."},            },            "required": ["a", "b"],            "additionalProperties": False,        },    },}] def multiply(a: int, b: int) -> int:    return a * b functions = {"multiply": multiply}messages = [{"role": "user", "content": "استخدم الأداة لحساب حاصل ضرب 125 في 48."}] def complete(tool_choice):    return client.chat.completions.create(        model="karnak-th-41b-v1.0",        messages=messages,        tools=tools,        tool_choice=tool_choice,        temperature=0.7,        top_p=0.8,        presence_penalty=1.0,        max_tokens=1024,        extra_body={            "top_k": 20,            "chat_template_kwargs": {"enable_thinking": False},        },    ).choices[0].message message = complete("auto")if message.tool_calls:    messages.append(message.model_dump(exclude_none=True))    for call in message.tool_calls:        arguments = json.loads(call.function.arguments)        result = functions[call.function.name](**arguments)        messages.append({            "role": "tool",            "tool_call_id": call.id,            "content": json.dumps({"result": result}),        })    message = complete("none") print(message.content)

Only expose functions your application intends to provide, and validate arguments before executing tools that access external services or modify data.

3. vLLM Offline Inference

Apply the model's chat template before submitting prompts for offline generation:

python

from transformers import AutoTokenizerfrom vllm import LLM, SamplingParams model_id = "Applied-Innovation-Center/Karnak-Th-41B-v1.0"tokenizer = AutoTokenizer.from_pretrained(model_id) llm = LLM(    model=model_id,    dtype="bfloat16",    tensor_parallel_size=2,) messages = [{"role": "user", "content": "Explain reinforcement learning in simple English."}]prompt = tokenizer.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True,    enable_thinking=False,) params = SamplingParams(    temperature=0.7,    top_p=0.8,    top_k=20,    presence_penalty=1.0,    max_tokens=1024,) for output in llm.generate([prompt], params):    print(output.outputs[0].text)

from transformers import AutoTokenizerfrom vllm import LLM, SamplingParams model_id = "Applied-Innovation-Center/Karnak-Th-41B-v1.0"tokenizer = AutoTokenizer.from_pretrained(model_id) llm = LLM(    model=model_id,    dtype="bfloat16",    tensor_parallel_size=2,) messages = [{"role": "user", "content": "Explain reinforcement learning in simple English."}]prompt = tokenizer.apply_chat_template(    messages,    tokenize=False,    add_generation_prompt=True,    enable_thinking=False,) params = SamplingParams(    temperature=0.7,    top_p=0.8,    top_k=20,    presence_penalty=1.0,    max_tokens=1024,) for output in llm.generate([prompt], params):    print(output.outputs[0].text)

Generation Guidance

We recommend setting presence_penalty=1.0 in both thinking and non-thinking modes when supported by the inference backend. All vLLM generation examples above use this setting.

Adjust temperature, sampling thresholds, and output budgets to your application's requirements.

Explicitly select thinking or non-thinking mode through the chat template.
Give thinking requests sufficient output budget; generation can stop before the final answer if reasoning consumes the token limit.
Use the checkpoint's tokenizer and generation configuration, including its end-of-sequence tokens.
Match serving settings to the checkpoint configuration, available memory, and application workload.

Intended Uses and Limitations

License

Karnak-Th-41B v1.0 is released under the Apache License 2.0. See the repository's LICENSE file for the full terms.

Citation

bibtex

@misc{karnak_th_41b_v1_2026,  title        = {Karnak-Th-41B v1.0: A Depth-Extended Arabic-English Language Model with Hybrid Thinking},  author       = {{Applied Innovation Center}},  year         = {2026},  howpublished = {Hugging Face model release},  url          = {https://huggingface.co/Applied-Innovation-Center/Karnak-Th-41B-v1.0}}

@misc{karnak_th_41b_v1_2026,  title        = {Karnak-Th-41B v1.0: A Depth-Extended Arabic-English Language Model with Hybrid Thinking},  author       = {{Applied Innovation Center}},  year         = {2026},  howpublished = {Hugging Face model release},  url          = {https://huggingface.co/Applied-Innovation-Center/Karnak-Th-41B-v1.0}}