From 52a721a2a945b106be0f48e71a3cb2b6ea642d9d Mon Sep 17 00:00:00 2001 From: joecummings Date: Fri, 11 Oct 2024 07:30:59 -0700 Subject: [PATCH] Remove generation config --- recipes/configs/qwen2/generation.yaml | 45 --------------------------- 1 file changed, 45 deletions(-) delete mode 100644 recipes/configs/qwen2/generation.yaml diff --git a/recipes/configs/qwen2/generation.yaml b/recipes/configs/qwen2/generation.yaml deleted file mode 100644 index 44d543b2f..000000000 --- a/recipes/configs/qwen2/generation.yaml +++ /dev/null @@ -1,45 +0,0 @@ -# Config for running the InferenceRecipe in generate.py to generate output from an LLM -# -# To launch, run the following command: -# tune run generate --config qwen2/generation - -# Model Arguments -model: - _component_: torchtune.models.qwen2.qwen2_7b - -# Checkpointer -checkpointer: - _component_: torchtune.training.FullModelHFCheckpointer - checkpoint_dir: /tmp/Qwen2-7B-Instruct - checkpoint_files: [ - model-00001-of-00004.safetensors, - model-00002-of-00004.safetensors, - model-00003-of-00004.safetensors, - model-00004-of-00004.safetensors - ] - output_dir: ./ # Not needed - model_type: QWEN2 - -# Tokenizer -tokenizer: - _component_: torchtune.models.qwen2.qwen2_tokenizer - path: /tmp/Qwen2-7B-Instruct/vocab.json - merges_file: /tmp/Qwen2-7B-Instruct/merges.txt - max_seq_len: null - -device: cuda -dtype: bf16 - -seed: 1234 - -# Generation arguments; defaults taken from gpt-fast -prompt: Tell me a joke. -instruct_template: null -chat_format: null -max_new_tokens: 300 -temperature: 0.6 # 0.8 and 0.6 are popular values to try -top_k: 300 - -enable_kv_cache: True - -quantizer: null