初始化项目，由ModelHub XC社区提供模型

Model: OpenAssistant/pythia-12b-pre-v8-12.5k-steps Source: Original Platform
2026-07-06 20:31:40 +08:00
commit 6e8d8e29b1
12 changed files with 101544 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,120 @@
+---
+license: apache-2.0
+---
+
+**Note: internal model, not ready for use**
+
+This is an intermediate model used as base-model for further pythia 12b SFT-8 experiments. 
+It was trained on a wider set of instruction-tuning datasets for >12.5k steps with batch-size 128 and a context size of 2048.
+The gpt4all dataset had "as a language model" *contamination* (>1.8k entries). We added filtering later, but this model (pre-v8) was trained on the raw unfildered gpt4all dataset.
+
+
+- wandb: https://wandb.ai/open-assistant/supervised-finetuning/runs/sytsyhrp
+- [sampling report](https://open-assistant.github.io/oasst-model-eval/?f=https%3A%2F%2Fraw.githubusercontent.com%2FOpen-Assistant%2Foasst-model-eval%2Fmain%2Fsampling_reports%2Foasst-pretrained%2F2023-05-05_OpenAssistant_pythia-12b-pre-v8-12_5k-steps_sampling_noprefix2.json)
+
+
+Datasets: 
+
+```
+pretrain:
+  num_train_epochs: 1
+  weight_decay: 0.0
+  use_custom_sampler: true
+  sort_by_length: false
+  datasets:
+    - gpteacher_roleplay:
+        val_split: 0.05
+    - red_pajama:
+        fraction: 0.25
+        max_val_set: 1000
+    - wizardlm_70k:
+        val_split: 0.05
+        max_val_set: 500
+    - joke:
+        val_split: 0.05
+    - poem_instructions:
+        val_split: 0.025
+    - oa_stackexchange:
+        val_split: 0.05
+        fraction: 0.1
+        max_val_set: 1000
+    - tell_a_joke:
+        val_split: 0.05
+        max_val_set: 250
+    - webgpt:
+        val_split: 0.05
+        max_val_set: 250
+    - gpt4all:
+        val_split: 0.01
+        max_val_set: 1000
+    - alpaca_gpt4:
+        val_split: 0.025
+        max_val_set: 250
+    - code_alpaca:
+        val_split: 0.05
+        max_val_set: 250
+    - vicuna:
+        max_val_set: 250
+    - oig_file:
+        source_url: https://huggingface.co/datasets/laion/OIG/resolve/main/unified_chip2.jsonl
+        max_count: 10000
+        min_length: 250
+        val_split: 0.05
+        max_val_set: 250
+    - minimath:
+        val_split: 0.05
+    - humaneval_mbpp_codegen_qa:
+        val_split: 0.05
+    - humaneval_mbpp_testgen_qa:
+        val_split: 0.05
+    - grade_school_math_instructions:
+        val_split: 0.05
+    - recipes:
+        val_split: 0.05
+    - cmu_wiki_qa:
+        val_split: 0.05
+ - oa_wiki_qa_bart_10000row:
+        val_split: 0.05
+        max_val_set: 250
+    - prosocial_dialogue:
+        fraction: 0.1
+        max_val_set: 250
+    - explain_prosocial:
+        fraction: 0.075
+        max_val_set: 250
+    - soda:
+        fraction: 0.25
+        max_val_set: 1000
+    - oa_leet10k:
+        val_split: 0.05
+        max_val_set: 250
+    - dolly15k:
+        val_split: 0.05
+        max_val_set: 300
+```
+
+
+Pythia:
+```
+pythia-12b-pretrain:
+  dtype: fp16
+  log_dir: "pythia_log_12b"
+  learning_rate: 6e-6
+  model_name: EleutherAI/pythia-12b-deduped
+  output_dir: pythia_model_12b
+  weight_decay: 0.0
+  max_length: 2048
+  warmup_steps: 100
+  gradient_checkpointing: true
+  gradient_accumulation_steps: 4
+  per_device_train_batch_size: 4
+  per_device_eval_batch_size: 4
+  eval_steps: 251
+  save_steps: 500
+  num_train_epochs: 1
+  save_total_limit: 2
+  deepspeed_config: configs/zero_config_pretrain.json
+```
+
+
+Command used: `deepspeed trainer_sft.py --show_dataset_stats --configs defaults pythia-12b-pretrain pretrain --cache_dir .cache/ --output_dir .saved/pythia-12b-super-pretrain2 --deepspeed`