初始化项目，由ModelHub XC社区提供模型
Model: mhenrichsen/danskgpt-tiny-chat 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
|
||||
127
README.md
Normal file
127
README.md
Normal file
@@ -0,0 +1,127 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
base_model: mhenrichsen/danskgpt-tiny
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
widget:
|
||||
- text: "<|im_start|>system\nDu er en hjælpsom assistent.<|im_end|>\n<|im_start|>user\nHvad er skak?<|im_end|>\n<|im_start|>assistant"
|
||||
example_title: "Skak"
|
||||
- text: "<|im_start|>system\nDu er en hjælpsom assistent.<|im_end|>\n<|im_start|>user\nHvem har lavet dig?<|im_end|>\n<|im_start|>assistant"
|
||||
example_title: "Skaber"
|
||||
|
||||
---
|
||||
|
||||
|
||||
# DanskGPT-tiny-chat
|
||||
<img src="danskgpt-tiny-chat.webp" width="500" height="500">
|
||||
|
||||
DanskGPT-tiny-chat er chat-varianten af [mhenrichsen/danskgpt-tiny](https://huggingface.co/mhenrichsen/danskgpt-tiny) trænet på private chat datasæt.
|
||||
|
||||
|
||||
## Model beskrivelse
|
||||
|
||||
Modellen er beregnet til at være en lightweight version af DanskGPT, der kan køre på næsten alle enheder.
|
||||
|
||||
## Prompt template
|
||||
|
||||
Modellen er trænet med ChatML format (samme som OpenAI's modeller), og skal bruges på følgende måde:
|
||||
|
||||
```
|
||||
<|im_start|>system\nDu er en hjælpsom assistent.<|im_end|>\n<|im_start|>user\nHvad er skak?<|im_end|>\n<|im_start|>assistant
|
||||
|
||||
```
|
||||
|
||||
|
||||
## Inferens
|
||||
|
||||
### Ollama
|
||||
Installér ollama:
|
||||
https://ollama.ai/download
|
||||
|
||||
Kør:
|
||||
```
|
||||
ollama run mhenrichsen/danskgpt-tiny-chat
|
||||
```
|
||||
|
||||
|
||||
### vLLM
|
||||
```
|
||||
pip install vllm
|
||||
```
|
||||
|
||||
|
||||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
|
||||
sampling_params = SamplingParams(temperature=0.8, top_p=0.95, max_tokens=1024)
|
||||
llm = LLM(model="mhenrichsen/danskgpt-tiny-chat")
|
||||
|
||||
system_message = "Du er en hjælpsom assistent."
|
||||
conversation_history = f"<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n"
|
||||
while True:
|
||||
prompt = input("Bruger: ")
|
||||
new_prompt = f"{conversation_history}{prompt}<|im_end|>\n<|im_start|>assistant\n"
|
||||
|
||||
outputs = llm.generate(new_prompt, sampling_params)
|
||||
for output in outputs:
|
||||
prompt = output.prompt
|
||||
generated_text = output.outputs[0].text
|
||||
print(f"AI: {generated_text!r}")
|
||||
conversation_history = f"{prompt}{generated_text!r}<|im_end|>\n<|im_start|>user\n"
|
||||
|
||||
```
|
||||
|
||||
### Endpoint med openai
|
||||
```
|
||||
pip install openai
|
||||
```
|
||||
|
||||
|
||||
```
|
||||
python -m vllm.entrypoints.openai.api_server --model mhenrichsen/danskgpt-tiny-chat
|
||||
```
|
||||
og brugt som erstatning for OpenAI's endpoints:
|
||||
|
||||
```python
|
||||
from openai import OpenAI
|
||||
openai_api_key = "EMPTY"
|
||||
openai_api_base = "http://localhost:8000/v1"
|
||||
|
||||
client = OpenAI(
|
||||
api_key=openai_api_key,
|
||||
base_url=openai_api_base,
|
||||
)
|
||||
|
||||
chat_response = client.chat.completions.create(
|
||||
model="mhenrichsen/danskgpt-tiny-chat",
|
||||
messages=[
|
||||
{"role": "system", "content": "Du er en hjælpsom assistent. Giv mig et langt svar."},
|
||||
{"role": "user", "content": "Fortæl mig om Danmark."},
|
||||
]
|
||||
)
|
||||
print("AI:", chat_response)
|
||||
```
|
||||
|
||||
|
||||
## Training results
|
||||
|
||||
|
||||
| Training Loss | Epoch | Step | Validation Loss |
|
||||
|:-------------:|:-----:|:----:|:---------------:|
|
||||
| 1.3599 | 0.0 | 1 | 1.4118 |
|
||||
| 0.7896 | 0.25 | 136 | 0.7813 |
|
||||
| 0.7339 | 0.5 | 272 | 0.7490 |
|
||||
| 0.7378 | 0.75 | 408 | 0.7285 |
|
||||
| 0.7112 | 1.0 | 544 | 0.7146 |
|
||||
| 0.6377 | 1.23 | 680 | 0.7135 |
|
||||
| 0.6192 | 1.49 | 816 | 0.7133 |
|
||||
| 0.5985 | 1.74 | 952 | 0.7073 |
|
||||
| 0.6067 | 1.99 | 1088 | 0.7026 |
|
||||
| 0.5139 | 2.22 | 1224 | 0.7167 |
|
||||
| 0.5099 | 2.47 | 1360 | 0.7193 |
|
||||
| 0.5217 | 2.72 | 1496 | 0.7168 |
|
||||
|
||||
## Brug for hjælp?
|
||||
Har du spørgsmål eller brug for hjælp til LLM'er eller automatisering af tekstbaserede opgaver, så kontakt mig gerne.
|
||||
|
||||
/Mads
|
||||
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 @@
|
||||
{
|
||||
"_name_or_path": "mhenrichsen/danskgpt-tiny",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"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": "bfloat16",
|
||||
"transformers_version": "4.37.0.dev0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32002
|
||||
}
|
||||
BIN
danskgpt-tiny-chat.webp
Normal file
BIN
danskgpt-tiny-chat.webp
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 247 KiB |
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": "4.37.0.dev0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a8e895ddc2c627898cdb2409b2f95cbfabe9ba494729cddf3765f6066664879
|
||||
size 2200136248
|
||||
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 sha256:4fc2b5e0d65c3aa53dd58c384a423ea64d2aa79263d9610b7004533c6a9efa99
|
||||
size 2200140157
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"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": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
61
tokenizer_config.json
Normal file
61
tokenizer_config.json
Normal file
@@ -0,0 +1,61 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"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": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'Du er en hjælpsom assistent.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|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": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"trust_remote_code": false,
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user