初始化项目，由ModelHub XC社区提供模型
Model: lightblue/karasu-1.1B Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
92
README.md
Normal file
92
README.md
Normal file
@@ -0,0 +1,92 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
license_name: tongyi-qianwen-license-agreement
|
||||
license_link: >-
|
||||
https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT
|
||||
datasets:
|
||||
- oscar-corpus/OSCAR-2301
|
||||
- mc4
|
||||
language:
|
||||
- ja
|
||||
---
|
||||
|
||||
<p align="center">
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/64c8a2e01c25d2c581a381c1/9CbN4lDGU42c-7DmK_mGM.png" alt="drawing" width="600"/>
|
||||
</p>
|
||||
|
||||
TinyLlama + Japanese pre-training (50,004 steps)
|
||||
|
||||
# How to use
|
||||
|
||||
|
||||
### Hugggingface
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("lightblue/karasu-1.1B")
|
||||
model = AutoModelForCausalLM.from_pretrained("lightblue/karasu-1.1B", torch_dtype=torch.bfloat16, device_map="auto")
|
||||
|
||||
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
|
||||
|
||||
messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
|
||||
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
|
||||
|
||||
prompt = tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
|
||||
|
||||
pipe(prompt, max_new_tokens=100, do_sample=False, temperature=0.0, return_full_text=False)
|
||||
```
|
||||
|
||||
|
||||
### VLLM
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
|
||||
sampling_params = SamplingParams(temperature=0.0, max_tokens=100)
|
||||
llm = LLM(model="lightblue/karasu-1.1B")
|
||||
|
||||
messages = [{"role": "system", "content": "あなたはAIアシスタントです。"}]
|
||||
messages.append({"role": "user", "content": "イギリスの首相は誰ですか？"})
|
||||
prompt = llm.llm_engine.tokenizer.apply_chat_template(conversation=messages, add_generation_prompt=True, tokenize=False)
|
||||
prompts = [prompt]
|
||||
|
||||
outputs = llm.generate(prompts, sampling_params)
|
||||
for output in outputs:
|
||||
prompt = output.prompt
|
||||
generated_text = output.outputs[0].text
|
||||
print(f"Prompt: {prompt!r}, Generated text: {generated_text!r}")
|
||||
```
|
||||
|
||||
|
||||
|
||||
# Base checkpoint
|
||||
[TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-715k-1.5T)
|
||||
|
||||
# Training datasets (total ~3B)
|
||||
A filtered then sampled set from
|
||||
* OSCAR (Japanese)
|
||||
* mC4 (Japanese)
|
||||
|
||||
# Developed by
|
||||
|
||||
<a href="https://www.lightblue-tech.com">
|
||||
<img src="https://www.lightblue-tech.com/wp-content/uploads/2023/08/color_%E6%A8%AA%E5%9E%8B-1536x469.png" alt="Lightblue technology logo" width="400"/>
|
||||
</a>
|
||||
|
||||
### Engineers
|
||||
Peter Devine
|
||||
|
||||
Sho Higuchi
|
||||
|
||||
### Advisors
|
||||
Yuuki Yamanaka
|
||||
|
||||
Atom Sonoda
|
||||
|
||||
### Project manager
|
||||
Shunichi Taniguchi
|
||||
|
||||
Tomioka Wataru
|
||||
|
||||
### Dataset evaluator
|
||||
Renju Aoki
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "ja_pretrained_tiny_llama",
|
||||
"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,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.31.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"max_length": 2048,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.31.0"
|
||||
}
|
||||
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d74059fadb8237363aa4e50d69b5a431c536d2e036c223f5e4cebca73f5dca3a
|
||||
size 4400268161
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
41
tokenizer_config.json
Normal file
41
tokenizer_config.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"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>",
|
||||
"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": false
|
||||
}
|
||||
Reference in New Issue
Block a user