初始化项目,由ModelHub XC社区提供模型
Model: gitcoreai/gpt-2-small-sft Source: Original Platform
This commit is contained in:
commit
03be28e686
7 files changed
+250470
No files matched your search
@@ -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
|
||||
@@ -0,0 +1,42 @@
|
||||
---
|
||||
license: mit
|
||||
base_model: openai-community/gpt2
|
||||
datasets:
|
||||
- OpenAssistant/oasst1
|
||||
language:
|
||||
- en
|
||||
pipeline_tag: text-generation
|
||||
library_name: transformers
|
||||
tags:
|
||||
- gpt2
|
||||
- gpt-2
|
||||
- chatbot
|
||||
- text-generation-inference
|
||||
---
|
||||
|
||||
# GPT-2 SFT on OASST1
|
||||
|
||||
This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on the [OpenAssistant/oasst1](https://huggingface.co/datasets/OpenAssistant/oasst1) dataset.
|
||||
|
||||
## Training Procedure
|
||||
|
||||
- **Base Model:** GPT-2 Small (124M parameters)
|
||||
- **Dataset:** OpenAssistant OASST1 (English only)
|
||||
- **Format:** `user: ... assistant: <s> ... </s>`
|
||||
- **Epochs:** 15
|
||||
- **Learning Rate:** 5e-5
|
||||
- **Batch Size:** 4 (effective 16 with gradient accumulation)
|
||||
|
||||
## Usage
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
model_name = "gitcoreai/gpt-2-small-sft"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
||||
model = AutoModelForCausalLM.from_pretrained(model_name)
|
||||
|
||||
prompt = "user: hello, how are you?\nassistant: <s>"
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
outputs = model.generate(**inputs, max_new_tokens=60)
|
||||
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
||||
+41
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"activation_function": "gelu_new",
|
||||
"add_cross_attention": false,
|
||||
"architectures": [
|
||||
"GPT2LMHeadModel"
|
||||
],
|
||||
"attn_pdrop": 0.1,
|
||||
"bos_token_id": 50256,
|
||||
"dtype": "float32",
|
||||
"embd_pdrop": 0.1,
|
||||
"eos_token_id": 50256,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gpt2",
|
||||
"n_ctx": 1024,
|
||||
"n_embd": 768,
|
||||
"n_head": 12,
|
||||
"n_inner": null,
|
||||
"n_layer": 12,
|
||||
"n_positions": 1024,
|
||||
"pad_token_id": 50256,
|
||||
"reorder_and_upcast_attn": false,
|
||||
"resid_pdrop": 0.1,
|
||||
"scale_attn_by_inverse_layer_idx": false,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"task_specific_params": {
|
||||
"text-generation": {
|
||||
"do_sample": true,
|
||||
"max_length": 50
|
||||
}
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.5.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 50259
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 50256,
|
||||
"eos_token_id": [
|
||||
50256
|
||||
],
|
||||
"pad_token_id": 50256,
|
||||
"transformers_version": "5.5.1"
|
||||
}
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf7ed8b0edc820aad016d4760251838d8b448ba4f08d38da6a8d8a39a8715dcb
|
||||
size 497780352
|
||||
+250324
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,16 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"is_local": false,
|
||||
"model_max_length": 1024,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
Reference in new issue
Block a user