--- license: apache-2.0 tags: - Safetensors - mistral - text-generation-inference - merge - mistral - 7b - mistralai/Mistral-7B-Instruct-v0.1 - chargoddard/piano-medley-7b - transformers - safetensors - mistral - text-generation - merge - mergekit - dataset:pankajmathur/orca_mini_v1_dataset - dataset:openai/summarize_from_feedback - dataset:PygmalionAI/PIPPA - dataset:chargoddard/rpguild - dataset:lemonilia/LimaRP - dataset:PKU-Alignment/PKU-SafeRLHF - dataset:Intel/orca_dpo_pairs - dataset:allenai/ultrafeedback_binarized_cleaned - license:cc-by-nc-4.0 - autotrain_compatible - endpoints_compatible - text-generation-inference - region:us --- # piano-medley-7b-Mistral-7B-Instruct-v0.1 piano-medley-7b-Mistral-7B-Instruct-v0.1 is a merge of the following models: * [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) * [chargoddard/piano-medley-7b](https://huggingface.co/chargoddard/piano-medley-7b) ## 🧩 Configuration ```yaml slices: - sources: - model: mistralai/Mistral-7B-Instruct-v0.1 layer_range: [0, 32] - model: chargoddard/piano-medley-7b layer_range: [0, 32] merge_method: slerp base_model: mistralai/Mistral-7B-Instruct-v0.1 parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "MaziyarPanahi/piano-medley-7b-Mistral-7B-Instruct-v0.1" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ```