初始化项目，由ModelHub XC社区提供模型

Model: haykgrigorian/v2mini-eval2
Source: Original Platform

.gitattributes

@@ -0,0 +1,50 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE.txt

@@ -0,0 +1,21 @@
+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.

README.md

@@ -0,0 +1,64 @@
+---
+license: mit
+datasets:
+- haykgrigorian/TimeCapsuleLLM-London-1800-1875-v2-15GB
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+
+# haykgrigorian/v2mini-eval2: Llama-Architecture 215M Model
+
+## Model Overview
+
+**v2mini-eval2** model, trained from scratch on 15GB of 1800-1875 london texts using Llama architecture. This model was trained to validate the tokenizer before scaling to 90GB.
+
+| Detail | Value |
+| :--- | :--- |
+| **Model Architecture** | LlamaForCausalLM (Decoder-Only Transformer) |
+| **Parameter Count** | **~215 Million (214.8M)** |
+| **Training Type** | Trained **from Scratch** (10,000 steps) |
+| **Tokenizer** | Custom BPE, Vocab Size 32,003 |
+| **Sequence Length** | 4096 tokens (4x increase from eval1) |
+| **Attention Type** | Grouped Query Attention (GQA) |
+
+## Configuration Details
+
+eval2 uses a different configuration comapared to eval1 for extended context length:
+
+| Parameter | Value |
+| :--- | :--- |
+| **Number of Layers** | 24 |
+| **Hidden Size (d)** | 768 |
+| **Intermediate Size ($\text{d}_{\text{ff}}$)** | 2048 |
+| **Attention Heads** | 12 (Query) / 6 (Key/Value) |
+| **Activation Function** | SiLU (`silu`) |
+| **Normalization** | RMS Norm (`rms_norm_eps`: 1e-05) |
+| **Position Embeddings** | RoPE (Theta: 10,000) |
+
+## Improvements & Fixes 
+
+* **Fixed Tokenization:** There was a spacing issue in the output from `eval1` (e.g., "D oes t ha t wor k") It's fixed now. Output should look normal.
+
+## Cost
+
+Total time in RunPod VM: 7:28 
+
+Total time spent on training: 5:52
+
+A100 SXM Cost: $1.49/Hour
+
+Total cost: $11.12
+
+
+### 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:** [test_v2mini_eval2.py on GitHub](https://github.com/haykgrigo3/TimeCapsuleLLM/blob/main/london_1800_1875_v2mini_eval1/test_v2mini_eval2.py)

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 6,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "vocab_size": 32003
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.57.3",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bfe0a23a60d493a6c7d7a1061f5b6cabc292d086a322902bf36bcb3f3066b4
+size 819655520

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<bos>",
+  "eos_token": "<eos>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75d85d260c0c0ecf3483d01c8866a9ba6174f22d6461b8340b014e353b54738
+size 2246930

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}