--- base_model: InferenceIllusionist/Magic-Dolphin-7b inference: false language: - en library_name: transformers license: apache-2.0 merged_models: - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser - Locutusque/Hyperion-1.5-Mistral-7B - ibm/merlinite-7b - autotrain_compatible - endpoints_compatible - text-generation-inference - chatml - mistral model-index: - name: Magic-Dolphin-7b results: - dataset: args: num_few_shot: 25 config: ARC-Challenge name: AI2 Reasoning Challenge (25-Shot) split: test type: ai2_arc metrics: - name: normalized accuracy type: acc_norm value: 65.78 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b task: name: Text Generation type: text-generation - dataset: args: num_few_shot: 10 name: HellaSwag (10-Shot) split: validation type: hellaswag metrics: - name: normalized accuracy type: acc_norm value: 85.61 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b task: name: Text Generation type: text-generation - dataset: args: num_few_shot: 5 config: all name: MMLU (5-Shot) split: test type: cais/mmlu metrics: - name: accuracy type: acc value: 64.64 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b task: name: Text Generation type: text-generation - dataset: args: num_few_shot: 0 config: multiple_choice name: TruthfulQA (0-shot) split: validation type: truthful_qa metrics: - type: mc2 value: 58.01 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b task: name: Text Generation type: text-generation - dataset: args: num_few_shot: 5 config: winogrande_xl name: Winogrande (5-shot) split: validation type: winogrande metrics: - name: accuracy type: acc value: 79.64 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b task: name: Text Generation type: text-generation - dataset: args: num_few_shot: 5 config: main name: GSM8k (5-shot) split: test type: gsm8k metrics: - name: accuracy type: acc value: 51.18 source: name: Open LLM Leaderboard url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b task: name: Text Generation type: text-generation model_creator: InferenceIllusionist model_name: Magic-Dolphin-7b model_type: mistral pipeline_tag: text-generation prompt_template: '<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ' quantized_by: Suparious tags: - mergekit - merge - code - quantized - 4-bit - AWQ - transformers --- # InferenceIllusionist/Magic-Dolphin-7b AWQ - Model creator: [InferenceIllusionist](https://huggingface.co/InferenceIllusionist) - Original model: [Magic-Dolphin-7b](https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b) ## Model Summary A linear merge of: - [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser) - [Locutusque/Hyperion-1.5-Mistral-7B](https://huggingface.co/Locutusque/Hyperion-1.5-Mistral-7B) - [ibm/merlinite-7b](https://huggingface.co/ibm/merlinite-7b) These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO. ## How to use ### Install the necessary packages ```bash pip install --upgrade autoawq autoawq-kernels ``` ### Example Python code ```python from awq import AutoAWQForCausalLM from transformers import AutoTokenizer, TextStreamer model_path = "solidrust/Magic-Dolphin-7b-AWQ" system_message = "You are Dolphin, incarnated as a powerful AI." # Load model model = AutoAWQForCausalLM.from_quantized(model_path, fuse_layers=True) tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True) # Convert prompt to tokens prompt_template = """\ <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant""" prompt = "You're standing on the surface of the Earth. "\ "You walk one mile south, one mile west and one mile north. "\ "You end up exactly where you started. Where are you?" tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt), return_tensors='pt').input_ids.cuda() # Generate output generation_output = model.generate(tokens, streamer=streamer, max_new_tokens=512) ``` ### About AWQ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings. AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead. It is supported by: - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types. - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference) - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code ## Prompt template: ChatML ```plaintext <|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant ```