初始化项目，由ModelHub XC社区提供模型

Model: simonko912/simllama-1.1-instruct
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+simllama11-inst.txt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- simllama
+- llama
+- smol-smoltalk
+- slm
+- 400m
+datasets:
+- HuggingFaceTB/smol-smoltalk
+- exnivo/tinybrain-instruct-sft-200k
+- OpenAssistant/oasst2
+- OpenAssistant/oasst1
+- drwlf/medra-thinking-768
+- togethercomputer/llama-instruct
+- interview-eval/MATH
+- RLAIF/mbpp
+---
+Checkpoint info: Loss around 1.8 when training. Epoch 2. More data unavaiable due to my trainer bugging out.<br>
+Loss on whole dataset: 2.0506176433255594 <br>
+Perplexity on whole dataset: 7.77 <br>
+Base model: https://huggingface.co/simonko912/simllama-1.1-base <br>
+
+| Dataset        | Loss  | Perplexity |
+|----------------|-------|------------|
+| WikiText-2     | 3.188 | 24.24      |
+| Penn Treebank  | 4.059 | 57.94      |
+| LAMBADA        | 3.656 | 38.70      |
+| C4             | 3.302 | 27.16      |
+
+Context: 4096 tokens total <br>
+Size: 0.4B <br>
+Extra info: Dense model, llama like arch. <br>
+
+### Examples
+````
+User: Make a hello world python program [/INST] 
+Full prompt format (leave empty for raw input): 
+
+Assistant: Here's an example Python program that takes in a string as input and prints it:
+```
+python
+def hello_world():
+    print("Hello, world!")
+```
+````
+````
+User: What is the capital of france? [/INST]
+Full prompt format (leave empty for raw input):
+
+Assistant: The capital of France is Paris.
+***
+Paris is famous for its historical landmarks and cultural institutions. Here are some of the most popular tourist attractions:
+* Clock Tower: This iconic clock tower is one of the most famous in the world, and it's also one of the most famous clocks in the world.
+* Notre Dame Cathedral: A beautiful Gothic cathedral with intricate carvings and a stunning view of the city.
+* La Plaza de la Seine: A beautiful and historic landmark, it's one of the most famous landmarks in the world.
+* Vatican City: A UNESCO World Heritage Site, the Vatican City is one of the world's largest and most visited tourist destinations.
+* Santa Cruz de la Catedral: A historic city with a rich history and culture, it's one of the most famous and vibrant cities in the world.
+* Santa Monica de los Nevis: A historic city with a rich history and cultural significance, it's one of the most famous tourist spots in the world.
+````

chat_template.jinja

@@ -0,0 +1,9 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ message['content'] }} [/INST]
+{% elif message['role'] == 'assistant' %}
+{{ message['content'] }}{% if not loop.last %} [INST]
+{% endif %}
+{% endif %}
+{% endfor %}
+{% if add_generation_prompt %}{% endif %}

config.json

@@ -0,0 +1,32 @@
+{
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47cedfcdb33c1821a8438fba32a0406521c585dd13d56e04bacf24c89d846ec4
+size 1872982408

simllama11-inst.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acaba21dc69991bf7e80f6033a5c6894908fbf45077f0daa1c049767d143fcfb
+size 2601361791

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ message['content'] }} [/INST]{% elif message['role'] == 'assistant' %}{{ message['content'] }}{% if not loop.last %} [INST]{% endif %}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "model_max_length": 4096,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}