初始化项目，由ModelHub XC社区提供模型

Model: appvoid/palmer-002.5
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+003.png filter=lfs diff=lfs merge=lfs -text
+palmer-002.5.gguf filter=lfs diff=lfs merge=lfs -text

003.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5229f1841c7da102dfd6fcb50dd3864cb884b647bdb9219588aee783584ea1f
+size 1228649

README.md

@@ -0,0 +1,38 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- merge
+---
+
+Creative writing has never been so accesible, palmer goes beyond what it was thought about small language models. This model is a "MErging of Experts" (MEoE) using `palmer-002-2401` as base, biased as an assistant without using any prompts—as a result of these efforts—palmer is better than most 1b language models on most benchmarks, despite being sometimes 40% smaller than its counterparts.
+
+```
+	              MMLU     ARC-C    OBQA   HellaSwag  PIQA  Winogrande Average
+tinyllama-chat | 0.2470 | 0.3285 | 0.3740 | 0.6037 | 0.7448 | 0.6022 | 0.4833 |
+zyte-1b	       | 0.2397 | 0.3353 | 0.3700 | 0.6086 | 0.7541 | 0.5998 | 0.4845 |
+palmer-002.5   | 0.2534 | 0.3370 | 0.3740 | 0.6128 | 0.7486 | 0.6535 | 0.4965 |
+qwen-1-8       | 0.4536 | 0.3490 | 0.3320 | 0.5876 | 0.7307 | 0.5896 | 0.5070 |
+```
+
+This work constitutes, given its compactness, an advancement towards SMLs, easily empowering edge devices such as mobile phones, raspberry pis and automated software/robots. Aditionally, palmer-002.5 deviates its main philosophy from palmer-family to become a more powerful model with more data instead of less.
+
+```
+prompt: Reality is but
+output: a dream,
+And the dreams we make are our reality.
+
+The world is a canvas, painted by our minds,
+And we can make it a masterpiece.
+
+So let us create, let us dream,
+And let our imagination run wild.
+
+For in our imagination lies our power,
+To create a world that is truly our own.
+```
+
+You can support me [through kofi](https://ko-fi.com/appvoid)
+
+Note that since this model uses a transformer architecture as any popular language model, its output sometimes contains hallucinations (make mistakes or false statements), and as such, it must be used with caution on sensitive scenarios.

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "appvoid/palmer-002-2401",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "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": "float16",
+  "transformers_version": "4.37.0.dev0",
+  "unsloth_version": "2024.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09eba1e4ab31aeb082987e4e898ea3e74661badd1d17b3816aaabd3747e8fc7
+size 2200119664

palmer-002.5.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8677cb5f0ec195dd208465b04e4b1eb8863ad108d82586d83b922960f6f7378c
+size 2201017344

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}