初始化项目，由ModelHub XC社区提供模型

Model: habanoz/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1 Source: Original Platform
2026-05-23 15:31:42 +08:00
commit 2cbb604314
16 changed files with 96124 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,170 @@
+---
+language:
+- en
+license: apache-2.0
+datasets:
+- OpenAssistant/oasst_top1_2023-08-25
+pipeline_tag: text-generation
+model-index:
+- name: tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 32.85
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 58.16
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.96
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 38.35
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 57.7
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=habanoz/tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1
+      name: Open LLM Leaderboard
+---
+
+TinyLlama-1.1B-intermediate-step-715k-1.5T finetuned using OpenAssistant/oasst_top1_2023-08-25 dataset.
+
+SFT code:
+https://github.com/jzhang38/TinyLlama/tree/main/sft
+
+Evaluation Results at:
+https://huggingface.co/datasets/open-llm-leaderboard/details_habanoz__tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1_public/blob/main/results_2023-11-23T17-25-53.937618.json
+
+Command used:
+```bash
+accelerate launch finetune.py \
+    --model_name_or_path TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T \
+    --output_dir ./output/1_5T_FT_lr1e-5_ep5_top1_2023-08-25 \
+    --logging_steps 10 \
+    --save_strategy epoch \
+    --data_seed 42 \
+    --save_total_limit 2 \
+    --evaluation_strategy epoch \
+    --eval_dataset_size 512 \
+    --max_eval_samples 1000 \
+    --per_device_eval_batch_size 1 \
+    --max_new_tokens 32 \
+    --dataloader_num_workers 3 \
+    --group_by_length=False \
+    --logging_strategy steps \
+    --remove_unused_columns False \
+    --do_train \
+    --do_eval \
+    --warmup_ratio 0.05 \
+    --lr_scheduler_type constant \
+    --dataset OpenAssistant/oasst_top1_2023-08-25 \
+    --dataset_format oasst1 \
+    --source_max_len 1 \
+    --target_max_len 1023 \
+    --per_device_train_batch_size 2 \
+    --gradient_accumulation_steps 8 \
+    --max_steps 0 \
+    --num_train_epochs 5 \
+    --learning_rate 1e-5 \
+    --adam_beta2 0.999 \
+    --max_grad_norm 1.0 \
+    --weight_decay 0.0 \
+    --seed 0 \
+    --trust_remote_code
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_habanoz__tinyllama-oasst1-top1-instruct-full-lr1-5-v0.1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |35.58|
+|AI2 Reasoning Challenge (25-Shot)|32.85|
+|HellaSwag (10-Shot)              |58.16|
+|MMLU (5-Shot)                    |25.96|
+|TruthfulQA (0-shot)              |38.35|
+|Winogrande (5-shot)              |57.70|
+|GSM8k (5-shot)                   | 0.45|
+
--- a/added_tokens.json
+++ b/added_tokens.json
@@ -0,0 +1,5 @@
+{
+  "<|im_end|>": 32002,
+  "<|im_start|>": 32001,
+  "[PAD]": 32000
+}
--- a/config.json
+++ b/config.json
@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": false,
+  "vocab_size": 32003
+}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,4 @@
+{
+  "max_new_tokens": 32,
+  "transformers_version": "4.31.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7e671102d45cfccf95c0e6358634a03f128490d8bb408ce40cad67ee1ef900
+size 4400271040
--- a/optimizer.pt
+++ b/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dff1c1ccc2f843f37b98e9ef2d3201432678e0fcfba462f61719ed925dddc96
+size 8800658482
--- a/pytorch_model.bin
+++ b/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98656cdc3cb658e5c9c614b7a6a8373c39a82a73addd5f1c28cadbce65a9ff5c
+size 4400320906
--- a/rng_state.pth
+++ b/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510b5bea665e30badb396a842fd0ce2871abed1251840cc1bd70ee16b88c258a
+size 14180
--- a/scheduler.pt
+++ b/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee523aaebf9a5639f449d144ff1e51abd768a2ec6e88d02e4c8c1649820d06fe
+size 1064
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "[PAD]",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
--- a/trainer_state.json
+++ b/trainer_state.json
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09840659b95c826a5ecfd883555afc96f5502a9ef6dc46e27ec0b7cadf65f389
+size 5880