Commit
•
67e0a45
1
Parent(s):
2dcb52c
Upload folder using huggingface_hub
Browse files- README.md +66 -0
- config.json +37 -0
- eval_results.json +16 -0
- generation_config.json +7 -0
- output.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
README.md
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
datasets:
|
4 |
+
- cerebras/SlimPajama-627B
|
5 |
+
- bigcode/starcoderdata
|
6 |
+
- HuggingFaceH4/ultrachat_200k
|
7 |
+
- HuggingFaceH4/ultrafeedback_binarized
|
8 |
+
language:
|
9 |
+
- en
|
10 |
+
widget:
|
11 |
+
- example_title: Fibonacci (Python)
|
12 |
+
messages:
|
13 |
+
- role: system
|
14 |
+
content: You are a chatbot who can help code!
|
15 |
+
- role: user
|
16 |
+
content: Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.
|
17 |
+
---
|
18 |
+
<div align="center">
|
19 |
+
|
20 |
+
# TinyLlama-1.1B
|
21 |
+
</div>
|
22 |
+
|
23 |
+
https://github.com/jzhang38/TinyLlama
|
24 |
+
|
25 |
+
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.
|
26 |
+
|
27 |
+
|
28 |
+
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.
|
29 |
+
|
30 |
+
#### This Model
|
31 |
+
This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT.
|
32 |
+
We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4."
|
33 |
+
|
34 |
+
|
35 |
+
#### How to use
|
36 |
+
You will need the transformers>=4.34
|
37 |
+
Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
|
38 |
+
|
39 |
+
```python
|
40 |
+
# Install transformers from source - only needed for versions <= v4.34
|
41 |
+
# pip install git+https://github.com/huggingface/transformers.git
|
42 |
+
# pip install accelerate
|
43 |
+
|
44 |
+
import torch
|
45 |
+
from transformers import pipeline
|
46 |
+
|
47 |
+
pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
|
48 |
+
|
49 |
+
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
50 |
+
messages = [
|
51 |
+
{
|
52 |
+
"role": "system",
|
53 |
+
"content": "You are a friendly chatbot who always responds in the style of a pirate",
|
54 |
+
},
|
55 |
+
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
56 |
+
]
|
57 |
+
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
58 |
+
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
59 |
+
print(outputs[0]["generated_text"])
|
60 |
+
# <|system|>
|
61 |
+
# You are a friendly chatbot who always responds in the style of a pirate.</s>
|
62 |
+
# <|user|>
|
63 |
+
# How many helicopters can a human eat in one sitting?</s>
|
64 |
+
# <|assistant|>
|
65 |
+
# ...
|
66 |
+
```
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 2048,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 5632,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 22,
|
16 |
+
"num_key_value_heads": 4,
|
17 |
+
"pretraining_tp": 1,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_scaling": null,
|
20 |
+
"rope_theta": 10000.0,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.35.0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000,
|
26 |
+
"quantization_config": {
|
27 |
+
"quant_method": "exl2",
|
28 |
+
"version": "0.1.5",
|
29 |
+
"bits": 4.6,
|
30 |
+
"head_bits": 6,
|
31 |
+
"calibration": {
|
32 |
+
"rows": 100,
|
33 |
+
"length": 2048,
|
34 |
+
"dataset": "(default)"
|
35 |
+
}
|
36 |
+
}
|
37 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_logits/chosen": -2.707406759262085,
|
4 |
+
"eval_logits/rejected": -2.656524419784546,
|
5 |
+
"eval_logps/chosen": -370.1297607421875,
|
6 |
+
"eval_logps/rejected": -296.0738525390625,
|
7 |
+
"eval_loss": 0.513750433921814,
|
8 |
+
"eval_rewards/accuracies": 0.738095223903656,
|
9 |
+
"eval_rewards/chosen": -0.02744222804903984,
|
10 |
+
"eval_rewards/margins": 1.0087225437164307,
|
11 |
+
"eval_rewards/rejected": -1.03616464138031,
|
12 |
+
"eval_runtime": 93.5908,
|
13 |
+
"eval_samples": 2000,
|
14 |
+
"eval_samples_per_second": 21.37,
|
15 |
+
"eval_steps_per_second": 0.673
|
16 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 1,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"max_length": 2048,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.0"
|
7 |
+
}
|
output.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0651789dc0f082881ace62a276836edf9144a6143489f5b9cc83fd0498ad714
|
3 |
+
size 740896096
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
}
|
27 |
+
},
|
28 |
+
"bos_token": "<s>",
|
29 |
+
"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 %}",
|
30 |
+
"clean_up_tokenization_spaces": false,
|
31 |
+
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
+
"model_max_length": 2048,
|
34 |
+
"pad_token": "</s>",
|
35 |
+
"padding_side": "right",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"tokenizer_class": "LlamaTokenizer",
|
38 |
+
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
+
}
|