初始化项目，由ModelHub XC社区提供模型

Model: invalid-coder/TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo
Source: Original Platform

.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

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

.ipynb_checkpoints/generation_config-checkpoint.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

README.md

@@ -0,0 +1,47 @@
+---
+license: apache-2.0
+datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+language:
+- en
+---
+<div align="center">
+
+# TinyLlama-1.1B-intermediate-step-1431k-3T-laser-dpo
+
+It follows the implementation of laserRMT @ https://github.com/cognitivecomputations/laserRMT
+and the novel training technique - we partially freeze the model according to a laser-like
+analysis (Official Paper soon) which effectively prevents the significant problem of language
+models forgetting previously acquired knowledge. This aspect is particularly crucial when attempting
+to teach the model specific skills, such as function calling.
+
+
+# TinyLlama-1.1B
+</div>
+
+https://github.com/jzhang38/TinyLlama
+
+The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 
+
+<div align="center">
+  <img src="./TinyLlama_logo.png" width="300"/>
+</div>
+
+We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
+
+#### This Collection
+This collection contains all checkpoints after the 1T fix. Branch name indicates the step and number of tokens seen.
+
+#### Eval
+
+| Model                                     | Pretrain Tokens | HellaSwag | Obqa | WinoGrande | ARC_c | ARC_e | boolq | piqa | avg |
+|-------------------------------------------|-----------------|-----------|------|------------|-------|-------|-------|------|-----|
+| Pythia-1.0B                               |        300B     | 47.16     | 31.40| 53.43      | 27.05 | 48.99 | 60.83 | 69.21 | 48.30 |
+| TinyLlama-1.1B-intermediate-step-50K-104b |        103B     | 43.50     | 29.80| 53.28      | 24.32 | 44.91 | 59.66 | 67.30 | 46.11|
+| TinyLlama-1.1B-intermediate-step-240k-503b|        503B     | 49.56     |31.40 |55.80       |26.54  |48.32  |56.91  |69.42  | 48.28 |
+| TinyLlama-1.1B-intermediate-step-480k-1007B |     1007B     | 52.54     | 33.40 | 55.96      | 27.82 | 52.36 | 59.54 | 69.91 | 50.22 |
+| TinyLlama-1.1B-intermediate-step-715k-1.5T |     1.5T     | 53.68     | 35.20 | 58.33      | 29.18 | 51.89 | 59.08 | 71.65 | 51.29 |
+| TinyLlama-1.1B-intermediate-step-955k-2T |     2T     | 54.63     | 33.40 | 56.83      | 28.07 | 54.67 | 63.21 | 70.67 | 51.64 |
+| TinyLlama-1.1B-intermediate-step-1195k-2.5T              |     2.5T     | 58.96     | 34.40 | 58.72      | 31.91 | 56.78 | 63.21 | 73.07 | 53.86|
+| TinyLlama-1.1B-intermediate-step-1431k-3T |     3T     | 59.20     | 36.00 | 59.12      | 30.12 | 55.25 | 57.83 | 73.29 | 52.99|

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.34.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36af52c4c0340d0f87ad69c5134d2c28760d187d47820a54834204b57070d011
+size 2200119864

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dbf9cbd21bc136fb581c73782ac24472c217e3bc90e6a131e5e4763516d3243
+size 2200164718

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}