Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) NeuralLLaMa-3-8b-DT-v0.1 - GGUF - Model creator: https://huggingface.co/Kukedlc/ - Original model: https://huggingface.co/Kukedlc/NeuralLLaMa-3-8b-DT-v0.1/ | Name | Quant method | Size | | ---- | ---- | ---- | | [NeuralLLaMa-3-8b-DT-v0.1.Q2_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q2_K.gguf) | Q2_K | 2.96GB | | [NeuralLLaMa-3-8b-DT-v0.1.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.IQ3_XS.gguf) | IQ3_XS | 3.28GB | | [NeuralLLaMa-3-8b-DT-v0.1.IQ3_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.IQ3_S.gguf) | IQ3_S | 3.43GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.41GB | | [NeuralLLaMa-3-8b-DT-v0.1.IQ3_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.IQ3_M.gguf) | IQ3_M | 3.52GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q3_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q3_K.gguf) | Q3_K | 3.74GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.74GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.03GB | | [NeuralLLaMa-3-8b-DT-v0.1.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.18GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q4_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q4_0.gguf) | Q4_0 | 4.34GB | | [NeuralLLaMa-3-8b-DT-v0.1.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.IQ4_NL.gguf) | IQ4_NL | 4.38GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.37GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q4_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q4_K.gguf) | Q4_K | 4.58GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.58GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q4_1.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q4_1.gguf) | Q4_1 | 4.78GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q5_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q5_0.gguf) | Q5_0 | 5.21GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.21GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q5_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q5_K.gguf) | Q5_K | 5.34GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.34GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q5_1.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q5_1.gguf) | Q5_1 | 5.65GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q6_K.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q6_K.gguf) | Q6_K | 6.14GB | | [NeuralLLaMa-3-8b-DT-v0.1.Q8_0.gguf](https://huggingface.co/RichardErkhov/Kukedlc_-_NeuralLLaMa-3-8b-DT-v0.1-gguf/blob/main/NeuralLLaMa-3-8b-DT-v0.1.Q8_0.gguf) | Q8_0 | 7.95GB | Original model description: --- tags: - merge - mergekit - lazymergekit - mlabonne/ChimeraLlama-3-8B-v2 - nbeerbower/llama-3-stella-8B - uygarkurt/llama-3-merged-linear base_model: - mlabonne/ChimeraLlama-3-8B-v2 - nbeerbower/llama-3-stella-8B - uygarkurt/llama-3-merged-linear license: other --- # NeuralLLaMa-3-8b-DT-v0.1 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/tK72e9RGnYyBVRy0T_Kba.png) NeuralLLaMa-3-8b-DT-v0.1 is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [mlabonne/ChimeraLlama-3-8B-v2](https://huggingface.co/mlabonne/ChimeraLlama-3-8B-v2) * [nbeerbower/llama-3-stella-8B](https://huggingface.co/nbeerbower/llama-3-stella-8B) * [uygarkurt/llama-3-merged-linear](https://huggingface.co/uygarkurt/llama-3-merged-linear) ## 🧩 Configuration ```yaml models: - model: NousResearch/Meta-Llama-3-8B # No parameters necessary for base model - model: mlabonne/ChimeraLlama-3-8B-v2 parameters: density: 0.33 weight: 0.2 - model: nbeerbower/llama-3-stella-8B parameters: density: 0.44 weight: 0.4 - model: uygarkurt/llama-3-merged-linear parameters: density: 0.55 weight: 0.4 merge_method: dare_ties base_model: NousResearch/Meta-Llama-3-8B parameters: int8_mask: true dtype: float16 ``` ## 🗨️ Chats ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/Uk89jeeRZ3Zh3wNBm6dXk.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64d71ab4089bc502ceb44d29/feYEkbM_TqeahAMOoiGoG.png) ## 💻 Usage ```python !pip install -qU transformers accelerate bitsandbytes from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, BitsAndBytesConfig import torch bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16 ) MODEL_NAME = 'Kukedlc/NeuralLLaMa-3-8b-DT-v0.1' tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME) model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config) prompt_system = "You are an advanced language model that speaks Spanish fluently, clearly, and precisely.\ You are called Roberto the Robot and you are an aspiring post-modern artist." prompt = "Create a piece of art that represents how you see yourself, Roberto, as an advanced LLm, with ASCII art, mixing diagrams, engineering and let yourself go." chat = [ {"role": "system", "content": f"{prompt_system}"}, {"role": "user", "content": f"{prompt}"}, ] chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) inputs = tokenizer(chat, return_tensors="pt").to('cuda') streamer = TextStreamer(tokenizer) stop_token = "<|eot_id|>" stop = tokenizer.encode(stop_token)[0] _ = model.generate(**inputs, streamer=streamer, max_new_tokens=1024, do_sample=True, temperature=0.7, repetition_penalty=1.2, top_p=0.9, eos_token_id=stop) ```