Commit History

6 days ago

  1. Update active Evaryx-Core API endpoint

    Verified signature
    d7658ce
  2. Update active Evaryx-Core API endpoint

    Verified signature
    bde0b21
  3. Update active Evaryx-Core API endpoint

    Verified signature
    2ca7c45

9 days ago

  1. Update README.md

    Verified signature
    1eae3c9
  2. --- language: - en library_name: transformers tags: - conversational - reasoning - text-generation - qwen2 - evaryx --- # Evaryx-Core (8B) **Evaryx-Core** is an 8-billion-parameter conversational and reasoning language model developed and fine-tuned by **EVARYX TECHNOLOGIES**. Built on the Qwen2 architecture, it is trained to deliver natural, human-like responses alongside structured, deep-thinking problem-solving. ## Key Capabilities - **Natural Communication:** Responds in a clear, fluid, and engaging tone without sounding robotic. - **Deep Thinking:** Breaks down complex questions, logic puzzles, and multi-step problems thoughtfully. - **General Problem Solving:** Assists with coding, brainstorming, explanations, and everyday decision-making. ## Model Details - **Developed by:** EVARYX TECHNOLOGIES - **Model Type:** Causal Language Model (Fine-tuned) - **Architecture:** Qwen2 (8B Parameters) - **Precision:** F16 (Safetensors) ## Quickstart (Python) ### Option 1: Standard Loading (16GB+ VRAM) ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "EvaryxTechnologies/Evaryx-Core" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto" ) messages = [ {"role": "user", "content": "Help me think through a complex problem step by step."} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True) print(response[0]) ``` ### Option 2: Low-Memory 4-Bit Loading (8GB VRAM) *Requires `bitsandbytes` (`pip install -U bitsandbytes accelerate transformers`).* ```python from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig model_id = "EvaryxTechnologies/Evaryx-Core" bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_compute_dtype="float16" ) tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, quantization_config=bnb_config, device_map="auto" ) messages = [ {"role": "user", "content": "Help me think through a complex problem step by step."} ] text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) model_inputs = tokenizer([text], return_tensors="pt").to(model.device) generated_ids = model.generate( **model_inputs, max_new_tokens=512 ) generated_ids = [ output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids) ] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True) print(response[0]) ``` ## Intended Use & Limitations Evaryx-Core is built for research, assistant applications, and general problem-solving. As with all language models, outputs should be verified for critical factual, medical, legal, or financial decisions.

    Verified signature
    e4938dc

10 days ago

  1. Upload tokenizer

    Verified signature
    7f87b6f
  2. Upload Qwen2ForCausalLM

    Verified signature
    705df66
  3. initial commit

    Verified signature
    2fb35a6