Add TinyLlama model version 3.0bpw

README.md

@@ -1,3 +1,58 @@
 ---
 license: apache-2.0
+datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+- OpenAssistant/oasst_top1_2023-08-25
+language:
+- en
 ---
+<div align="center">
+
+# TinyLlama-1.1B
+</div>
+
+https://github.com/jzhang38/TinyLlama
+
+The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 
+
+
+We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
+
+#### This Model
+This is the chat model finetuned on top of [PY007/TinyLlama-1.1B-intermediate-step-480k-1T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-480k-1T). 
+The dataset used is [OpenAssistant/oasst_top1_2023-08-25](https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25) following the [chatml](https://github.com/openai/openai-python/blob/main/chatml.md) format.
+#### How to use
+You will need the transformers>=4.31
+Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
+```
+from transformers import AutoTokenizer
+import transformers 
+import torch
+model = "PY007/TinyLlama-1.1B-Chat-v0.3"
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+prompt = "How to get in a good university?"
+formatted_prompt = (
+    f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+)
+
+
+sequences = pipeline(
+    formatted_prompt,
+    do_sample=True,
+    top_k=50,
+    top_p = 0.9,
+    num_return_sequences=1,
+    repetition_penalty=1.1,
+    max_new_tokens=1024,
+)
+for seq in sequences:
+    print(f"Result: {seq['generated_text']}")
+```

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|im_end|>": 32002,
+  "<|im_start|>": 32001,
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "PY007/TinyLlama-1.1B-intermediate-step-480k-1T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "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": "float32",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32003
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "max_new_tokens": 32,
+  "transformers_version": "4.34.0.dev0"
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0da87a7ed9fa47101da5d045d0e002f58568accd4a0746d12069287388d22c5c
+size 548629432

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac265c28d55ea9e393c0386a0effa02fd8b46015e85a561d7cf44d6a9a870d6
+size 4400310718

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}