初始化项目，由ModelHub XC社区提供模型
Model: Ramikan-BR/TiamaPY-v34 Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
unsloth.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
unsloth.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
128
README.md
Normal file
128
README.md
Normal file
@@ -0,0 +1,128 @@
|
||||
---
|
||||
base_model: unsloth/tinyllama-chat-bnb-4bit
|
||||
language:
|
||||
- en
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- text-generation-inference
|
||||
- transformers
|
||||
- unsloth
|
||||
- llama
|
||||
- trl
|
||||
- sft
|
||||
---
|
||||
``` Python
|
||||
# Question
|
||||
|
||||
if False:
|
||||
from unsloth import FastLanguageModel
|
||||
model, tokenizer = FastLanguageModel.from_pretrained(
|
||||
model_name = "lora_model", # YOUR MODEL YOU USED FOR TRAINING
|
||||
max_seq_length = max_seq_length,
|
||||
dtype = dtype,
|
||||
load_in_4bit = load_in_4bit,
|
||||
)
|
||||
FastLanguageModel.for_inference(model) # Enable native 2x faster inference
|
||||
|
||||
# alpaca_prompt = You MUST copy from above!
|
||||
|
||||
inputs = tokenizer(
|
||||
[
|
||||
alpaca_prompt.format(
|
||||
"Eu preciso treinar uma IA gpt2 do hugginface em meu computador", # instruction
|
||||
"", # input
|
||||
"", # output - leave this blank for generation!
|
||||
)
|
||||
], return_tensors = "pt").to("cuda")
|
||||
|
||||
from transformers import TextStreamer
|
||||
text_streamer = TextStreamer(tokenizer)
|
||||
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 4096)
|
||||
|
||||
# Answer
|
||||
|
||||
<s> Below is an instruction that describes a task related to Python programming or computer science concepts. Provide a detailed, accurate, and helpful response that addresses the query or solves the problem presented. Follow these guidelines:
|
||||
|
||||
1. If the task involves coding, provide a complete, working Python solution with explanations.
|
||||
2. If it's a conceptual question, explain thoroughly, using examples where appropriate.
|
||||
3. Break down complex problems or concepts into steps or components.
|
||||
4. If you're unsure about any part of your response, clearly state your level of confidence and any assumptions you're making.
|
||||
5. If the query is ambiguous or lacks necessary information, ask for clarification before proceeding.
|
||||
6. After providing your response, briefly summarize the key points or solution.
|
||||
|
||||
Remember, accuracy and helpfulness are crucial. Avoid making unfounded claims or providing incorrect information.
|
||||
|
||||
### Input:
|
||||
Eu preciso treinar uma IA gpt2 do hugginface em meu computador
|
||||
|
||||
### Output:
|
||||
|
||||
# Importações necessárias
|
||||
from transformers import GPT2LMHeadModel, GPT2Tokenizer
|
||||
from transformers import TrainingArguments, Trainer
|
||||
from transformers.data import DataCollatorForLanguageModeling
|
||||
from transformers.data.processors import DataProcessor
|
||||
|
||||
# Configurações
|
||||
training_args = TrainingArguments(
|
||||
output_dir='./resultados',
|
||||
evaluation_strategy='epoch',
|
||||
learning_rate=2e-5,
|
||||
per_device_train_batch_size=8,
|
||||
eval_steps=1000,
|
||||
num_warmupSteps=500,
|
||||
weighted_metric='accuracy',
|
||||
)
|
||||
|
||||
# Carregamento do tokenizador
|
||||
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
|
||||
|
||||
# Carregamento do modelo
|
||||
modelo = GPT2LMHeadModel.from_pretrained('gpt2')
|
||||
|
||||
# Configurações do tracker
|
||||
tracker = DataProcessor(
|
||||
input_class=DataProcessor,
|
||||
batch_size=1,
|
||||
max_length=100,
|
||||
padding=True,
|
||||
truncation=True,
|
||||
)
|
||||
|
||||
# Treinando o modelo
|
||||
trainer = Trainer(
|
||||
args=training_args,
|
||||
train_loop=tracker,
|
||||
trainable_pipelines=[],
|
||||
)
|
||||
|
||||
# Treinando o modelo
|
||||
trainer.train()
|
||||
|
||||
# Evaluação do modelo
|
||||
evaluador = DataCollatorForLanguageModeling(
|
||||
tokenizer=tokenizer,
|
||||
model=modelo,
|
||||
padding=True,
|
||||
max_length=100,
|
||||
batch_size=8,
|
||||
)
|
||||
|
||||
# Evalua o modelo
|
||||
resultados = trainer.evaluate()
|
||||
|
||||
# Imprimir os resultados
|
||||
for name, loss, acc in resultados:
|
||||
print(f'{name}: {loss}, {acc:.2f}%')</s>
|
||||
|
||||
```
|
||||
|
||||
# Uploaded model
|
||||
|
||||
- **Developed by:** Ramikan-BR
|
||||
- **License:** apache-2.0
|
||||
- **Finetuned from model :** unsloth/tinyllama-chat-bnb-4bit
|
||||
|
||||
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
|
||||
34
config.json
Normal file
34
config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"_name_or_path": "unsloth/tinyllama-chat-bnb-4bit",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5632,
|
||||
"max_position_embeddings": 4096,
|
||||
"mlp_bias": false,
|
||||
"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": {
|
||||
"factor": 2.0,
|
||||
"type": "linear"
|
||||
},
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.41.2",
|
||||
"unsloth_version": "2024.6",
|
||||
"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": "4.41.2"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4d0f4b1f48ff6239689ec6cb029c4cfd7c2f42a752adcf1245642271342b6d51
|
||||
size 2200119664
|
||||
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 sha256:2e55188af42ef6af31743c4d1be552b329645cd5c2a36bb79386ec207c2a73f8
|
||||
size 2200164718
|
||||
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": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93392
tokenizer.json
Normal file
93392
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
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
|
||||
42
tokenizer_config.json
Normal file
42
tokenizer_config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"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>",
|
||||
"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 %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": false,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<unk>",
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
3
unsloth.F16.gguf
Normal file
3
unsloth.F16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:25333c2c59decf3cba1d4051215d13d906e38ae1f0f1b11f664a13ec3adaca49
|
||||
size 2201017536
|
||||
3
unsloth.Q4_K_M.gguf
Normal file
3
unsloth.Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2be90d9736ee9f30d7ab6f2706a2693699c8689b64910dcc7b52ad6701391cb6
|
||||
size 667815104
|
||||
3
unsloth.Q8_0.gguf
Normal file
3
unsloth.Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b4bd753692851f4a6144817580d2f790083ad3b0fc78f1bb2f1acfdee9bcd99f
|
||||
size 1169808576
|
||||
Reference in New Issue
Block a user