初始化项目，由ModelHub XC社区提供模型

Model: croqaz/vintage-LLM-340m-v1-base
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

README.md

@@ -0,0 +1,25 @@
+---
+license: mit
+language:
+- en
+pipeline_tag: text-generation
+library_name: transformers
+datasets:
+- croqaz/vintage-v1
+---
+
+# Vintage-LLM
+
+This is a 340M params Llama3-based model, trained on text pre-1900.
+
+This is a base model. It has very limited chat capabilities.
+
+Dataset used: https://huggingface.co/datasets/croqaz/vintage-v1
+
+The data was de-duplicated and only the decent quality texts were used.
+
+There are a few checkpoints in the repo:
+
+- 10k steps on short texts: [commit/ff3b94efdaccfa312754d3a4328b7c7a05155d36](https://huggingface.co/croqaz/vintage-LLM-340m-v1-base/commit/ff3b94efdaccfa312754d3a4328b7c7a05155d36)
+- previous model + short ft on [vintage-FT-v1](https://huggingface.co/datasets/croqaz/vintage-ft-v1): [commit/3946781d51e76c7cf0874bd595003bce1755cbd2](https://huggingface.co/croqaz/vintage-LLM-340m-v1-base/commit/3946781d51e76c7cf0874bd595003bce1755cbd2)
+- previous model + 10k steps on long texts: [commit/c9b48cc3aaa4b3dc0ea3b846f45e98a05e94c8cb](https://huggingface.co/croqaz/vintage-LLM-340m-v1-base/commit/c9b48cc3aaa4b3dc0ea3b846f45e98a05e94c8cb)

chat_template.jinja

@@ -0,0 +1,7 @@
+{%- for message in messages %}
+  {{- bos_token + '<|' + message['role'] + '|>\n' + message['content'].strip() + eos_token + '\n'}}
+{% endfor -%}
+
+{%- if add_generation_prompt %}
+  {{- bos_token + '<|assistant|>\n'}}
+{% endif -%}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 3,
+  "dtype": "bfloat16",
+  "eos_token_id": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 65536,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "factor": 16.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 4096,
+    "rope_theta": 10000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.2",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 3,
+  "eos_token_id": [
+    4,
+    2
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.10.2",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e861b1755868099d902e519f96b51bacda30c862b9784c4225c8ded7429806
+size 681668904

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "eos_token": "<|eos|>",
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}