初始化项目，由ModelHub XC社区提供模型

Model: danielhanchen/open_llama_3b_600bt_preview
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.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
+*.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 +1,47 @@
+---
+license: apache-2.0
+language:
+- en
+---
+
+# ARCHIVED.
+## Download from original repo: https://huggingface.co/openlm-research/open_llama_3b_600bt_preview
+### I made a few PRs to the original repo to include my changes!
+Original model from https://huggingface.co/openlm-research/open_llama_3b_600bt_preview.
+Example below edited from https://github.com/openlm-research/open_llama
+```
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+model_name = "openlm-research/open_llama_3b_600bt_preview"
+fast_model_name = "danielhanchen/open_llama_3b_600bt_preview"
+
+tokenizer = AutoTokenizer.from_pretrained(fast_model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype = torch.float16, device_map = "auto")
+
+prompt = "Q: What is the largest animal?\nA:"
+input_ids = tokenizer(prompt, return_tensors = "pt").input_ids
+print( tokenizer.decode( model.generate( input_ids, max_new_tokens = 32).ravel() ) )
+```
+
+This repo includes:
+1) Ported `LlamaTokenizer` to `LlamaTokenizerFast` via a few lines of code.
+   Loading via `AutoTokenizer` takes 4 to 5 minutes. Now, a few seconds!
+   Essentially the porting is done via the below code:
+```
+# from huggingface_hub import notebook_login
+# notebook_login()
+from transformers import LlamaTokenizerFast
+from tokenizers import AddedToken
+tokenizer = LlamaTokenizerFast.from_pretrained(
+    "openlm-research/open_llama_3b_600bt_preview",
+    add_bos_token = True,
+    add_eos_token = False, # Original LLaMA is False -> add </s> during processing.
+    bos_token = AddedToken("<s>",   single_word = True),
+    eos_token = AddedToken("</s>",  single_word = True),
+    unk_token = AddedToken("<unk>", single_word = True),
+    pad_token = AddedToken("<unk>", single_word = True)
+)
+tokenizer.push_to_hub("open_llama_3b_600bt_preview")
+```
+2) `AutoTokenizer` does not recognize the BOS, EOS and UNK tokens. Weirdly `<unk>` ie the 0 token was added instead of the `<s>` or `</s>` token.
+3) Manually added BOS `<s>`, EOS `</s>`, UNK `<unk>` tokens, with PAD (padding) being also the `<unk>` token.

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "openlm-research/open_llama_3b_600bt_preview",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:627072072ec5e902d9f826e0f21ad3d2a13b17e42b6960a9f7e50f78c1e6df29
+size 6852982288

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ece3026bf9275baf0010bc27ec8fa05941f8d7830435f3c9cc8daa9f4219fa3
+size 6853041741

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
+size 534194

tokenizer_config.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>"
+}