初始化项目，由ModelHub XC社区提供模型
Model: OuteAI/Lite-Oute-1-65M-Instruct Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.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
|
||||
model.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
113
README.md
Normal file
113
README.md
Normal file
@@ -0,0 +1,113 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
---
|
||||
# Lite-Oute-1-65M-Instruct
|
||||
|
||||
Lite-Oute-1-65M-Instruct is an experimental ultra-compact model in the Lite series, based on the LLaMA architecture and comprising approximately 65 million parameters. <br>
|
||||
The primary goal of this model was to explore the lower limits of model size while still maintaining basic language understanding capabilities. <br>
|
||||
Due to its extremely small size, this model demonstrates basic text generation abilities but may struggle with instructions or maintaining topic coherence. <br>
|
||||
Users should be aware of its significant limitations compared to larger models and expect inconsistent or potentially inaccurate responses.
|
||||
|
||||
## Available versions:
|
||||
<a href="https://huggingface.co/OuteAI/Lite-Oute-1-65M-Instruct">Lite-Oute-1-65M-Instruct</a> <br>
|
||||
<a href="https://huggingface.co/OuteAI/Lite-Oute-1-65M-Instruct-GGUF">Lite-Oute-1-65M-Instruct-GGUF</a> <br>
|
||||
<a href="https://huggingface.co/OuteAI/Lite-Oute-1-65M">Lite-Oute-1-65M</a> <br>
|
||||
<a href="https://huggingface.co/OuteAI/Lite-Oute-1-65M-GGUF">Lite-Oute-1-65M-GGUF</a> <br>
|
||||
|
||||
## Chat format
|
||||
> [!IMPORTANT]
|
||||
> This model uses **ChatML** template. Ensure you use the correct template:
|
||||
|
||||
```
|
||||
<|im_start|>system
|
||||
[System message]<|im_end|>
|
||||
<|im_start|>user
|
||||
[Your question or message]<|im_end|>
|
||||
<|im_start|>assistant
|
||||
[The model's response]<|im_end|>
|
||||
```
|
||||
|
||||
<table style="text-align: left;">
|
||||
<tr>
|
||||
<th>Benchmark</th>
|
||||
<th>5-shot</th>
|
||||
<th>0-shot</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ARC Challenge</td>
|
||||
<td>22.61</td>
|
||||
<td>23.63</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ARC Easy</td>
|
||||
<td>37.16</td>
|
||||
<td>40.49</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>CommonsenseQA</td>
|
||||
<td>19.41</td>
|
||||
<td>20.64</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>HellaSWAG</td>
|
||||
<td>28.74</td>
|
||||
<td>28.41</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU</td>
|
||||
<td>25.20</td>
|
||||
<td>23.45</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>OpenBookQA</td>
|
||||
<td>27.40</td>
|
||||
<td>28.60</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>PIQA</td>
|
||||
<td>60.88</td>
|
||||
<td>60.77</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Winogrande</td>
|
||||
<td>50.59</td>
|
||||
<td>50.04</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Usage with HuggingFace transformers
|
||||
The model can be used with HuggingFace's `transformers` library:
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
||||
model = AutoModelForCausalLM.from_pretrained("OuteAI/Lite-Oute-1-65M-Instruct").to(device)
|
||||
tokenizer = AutoTokenizer.from_pretrained("OuteAI/Lite-Oute-1-65M-Instruct")
|
||||
def generate_response(message: str, temperature: float = 0.4, repetition_penalty: float = 1.12) -> str:
|
||||
# Apply the chat template and convert to PyTorch tensors
|
||||
messages = [
|
||||
{"role": "system", "content": "You are a helpful assistant."},
|
||||
{"role": "user", "content": message}
|
||||
]
|
||||
input_ids = tokenizer.apply_chat_template(
|
||||
messages, add_generation_prompt=True, return_tensors="pt"
|
||||
).to(device)
|
||||
# Generate the response
|
||||
output = model.generate(
|
||||
input_ids,
|
||||
max_length=512,
|
||||
temperature=temperature,
|
||||
repetition_penalty=repetition_penalty,
|
||||
do_sample=True
|
||||
)
|
||||
# Decode the generated output
|
||||
generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
|
||||
return generated_text
|
||||
message = "I'd like to learn about language models. Can you break down the concept for me?"
|
||||
response = generate_response(message)
|
||||
print(response)
|
||||
```
|
||||
|
||||
## Risk Disclaimer
|
||||
|
||||
By using this model, you acknowledge that you understand and assume the risks associated with its use. You are solely responsible for ensuring compliance with all applicable laws and regulations. We disclaim any liability for problems arising from the use of this open-source model, including but not limited to direct, indirect, incidental, consequential, or punitive damages. We make no warranties, express or implied, regarding the model's performance, accuracy, or fitness for a particular purpose. Your use of this model is at your own risk, and you agree to hold harmless and indemnify us, our affiliates, and our contributors from any claims, damages, or expenses arising from your use of the model.
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"<|im_end|>": 32000,
|
||||
"<|im_start|>": 32001
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 512,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 2048,
|
||||
"max_position_embeddings": 2048,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 8,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.42.4",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.42.4"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa35064993cfa8273037f673b3c62aedc3ef8c0f6b86ac1dbdc0eb7af4f5309f
|
||||
size 260089968
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91141
tokenizer.json
Normal file
91141
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.
64
tokenizer_config.json
Normal file
64
tokenizer_config.json
Normal file
@@ -0,0 +1,64 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": true,
|
||||
"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": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"legacy": true,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|im_end|>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user