初始化项目，由ModelHub XC社区提供模型

Model: haykgrigorian/TimeCapsuleLLM-v2-llama-1.2B Source: Original Platform
2026-06-28 07:44:12 +08:00
commit ab418684db
11 changed files with 262 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,51 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
--- a/22
+++ b/22
@@ -0,0 +1,22 @@
+
+ MIT License
+
+Copyright (c) 2025 Hayk Grigorian 
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
--- a/README.md
+++ b/README.md
@@ -0,0 +1,75 @@
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+tags:
+- llama
+- historical
+- causal-lm
+datasets:
+- postgrammar/london-llm-1800
+---
+# haykgrigorian/TimeCapsuleLLM-v2-London-1800-1875: Llama-Architecture 1.2B Model 
+
+## Model Overview
+
+**v2** model, trained from scratch on 112GB of 1800-1875 london texts using a Llama-based Casual Language Model.
+
+| Detail | Value |
+| :--- | :--- |
+| **Model Architecture** | LlamaForCausalLM (Decoder-Only Transformer) |
+| **Parameter Count** | **~1.22B** |
+| **Training Type** | Trained **from Scratch** (Random Initialization) |
+| **Tokenizer** | Custom BPE, Vocab Size 32,000 |
+| **Sequence Length** | 2048 tokens |
+| **Attention Type** | Grouped Query Attention (GQA) |
+
+## Configuration Details
+
+This model is a custom size and configuration based on Llama:
+
+| Parameter | Value |
+| :--- | :--- |
+| **Number of Layers** | 22 |
+| **Hidden Size (d)** | 2048 |
+| **Intermediate Size ($\text{d}_{\text{ff}}$)** | 5504 |
+| **Attention Heads** | 16 (Query) / 8 (Key/Value) |
+| **Activation Function** | SiLU (`silu`) |
+| **Normalization** | RMS Norm (`rms_norm_eps`: 1e-06) |
+| **Position Embeddings** | Rotary Positional Embeddings (RoPE) |
+
+## Training Info
+
+This model was trained for 182,000 steps, about 0.5 epochs.
+
+Training Metrics:
+
+Final Training Loss: 3.3951
+
+Start Training Loss: 10.7932
+
+Training Steps: 182,000
+
+Epochs: 0.4997
+
+Gradient Norm Stability: Consistently stable between 0.50 and 0.60 in later stages.
+
+Training time: 117 hours 51 minutes
+
+### Cost 
+
+This model was trained on an H100 SXM from RunPod 
+
+Total: $340.97
+
+### How to Load and Run the Model
+
+Install all the files locally in a folder and run the test script. You will have to make some adjustments in the run script like updating the config/file path and test prompts
+
+### Test script
+
+A run file for testing and evaluating this model is available on the main project repository:
+
+* **Test Script Link:** [run_v2.py on GitHub](https://github.com/haykgrigo3/TimeCapsuleLLM/blob/main/london_1800_1875_v2/run_v2.py)
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 8,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 32000
+}
--- a/configuration.json
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 3,
+  "transformers_version": "4.57.3",
+  "use_cache": false
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf27f60f381de286250ebc4f67d258fbecda13371600d41ab16c9b9b4b1493a
+size 2303928936
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/tokenizer.json
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21a8bb830725dc9ca405a610c415add7c32131d38f71fa4104dcb6389c7a65f
+size 2242737
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,60 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "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": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|year|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|title|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/training_args.bin
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81bf17b9e97afdcdab50b41c451885d58db58b267bfd58d96b902c7fb76693db
+size 5432
				`@@ -0,0 +1 @@`
				`{"framework": "pytorch", "task": "text-generation", "allow_remote": true}`