初始化项目，由ModelHub XC社区提供模型
Model: arif-butt/tinyllama-trl-merged 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
|
||||
112
README.md
Normal file
112
README.md
Normal file
@@ -0,0 +1,112 @@
|
||||
---
|
||||
language: en
|
||||
license: apache-2.0
|
||||
library_name: transformers
|
||||
tags:
|
||||
- tinyllama
|
||||
- trl
|
||||
- merged
|
||||
- lora
|
||||
- fine-tuned
|
||||
- pytorch
|
||||
- causal-lm
|
||||
- text-generation
|
||||
- conversational
|
||||
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
||||
datasets:
|
||||
- arif-butt/arifbutt_dataset
|
||||
pipeline_tag: text-generation
|
||||
inference: false
|
||||
---
|
||||
|
||||
# 🦙 TinyLlama TRL Merged - Complete Fine-tuned Model
|
||||
|
||||
## 📋 Model Overview
|
||||
|
||||
This is a **fully merged and standalone model** of TinyLlama (1.1B parameters) fine-tuned using **TRL (Transformer Reinforcement Learning)** framework with LoRA adapters. The LoRA weights have been permanently merged into the base model, creating a single complete model that can be loaded without any adapter libraries.
|
||||
|
||||
### Key Features
|
||||
| Feature | Description |
|
||||
|---------|-------------|
|
||||
| **Standalone** | No PEFT library required — single model file |
|
||||
| **Fine-tuned** | Custom trained on educational Q&A dataset |
|
||||
| **Optimized** | FP16 precision for memory efficiency |
|
||||
| **Production Ready** | Single folder deployment |
|
||||
| **Chat Optimized** | Fine-tuned for conversational responses |
|
||||
|
||||
### Model Architecture
|
||||
| Component | Specification |
|
||||
|-----------|---------------|
|
||||
| **Base Model** | TinyLlama-1.1B-Chat-v1.0 |
|
||||
| **Architecture** | Llama-based transformer decoder |
|
||||
| **Total Parameters** | 1,100,000,000 (1.1B) |
|
||||
| **Context Length** | 2048 tokens |
|
||||
| **Hidden Size** | 2048 |
|
||||
| **Intermediate Size** | 5632 |
|
||||
| **Number of Layers** | 22 |
|
||||
| **Number of Attention Heads** | 32 |
|
||||
| **Number of Key/Value Heads** | 4 (GQA) |
|
||||
| **Head Dimension** | 64 |
|
||||
| **Activation Function** | SwiGLU |
|
||||
| **Positional Encoding** | RoPE (Rotary Position Embedding) |
|
||||
| **Attention Mechanism** | Grouped-Query Attention (GQA) |
|
||||
| **Precision** | FP16 (float16) |
|
||||
|
||||
## 🚀 Usage Guide
|
||||
|
||||
### Installation
|
||||
```bash
|
||||
pip install transformers torch accelerate
|
||||
|
||||
Method 1: Direct Transformers Loading
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
import torch
|
||||
|
||||
# Load model and tokenizer
|
||||
model_id = "arif-butt/tinyllama-trl-merged"
|
||||
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
||||
model = AutoModelForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
trust_remote_code=True,
|
||||
)
|
||||
model.eval()
|
||||
|
||||
# Define prompt template
|
||||
prompt = "Q: What is machine learning?\nA:"
|
||||
|
||||
# Tokenize
|
||||
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
|
||||
|
||||
# Generate
|
||||
with torch.no_grad():
|
||||
outputs = model.generate(
|
||||
**inputs,
|
||||
max_new_tokens=150,
|
||||
temperature=0.7,
|
||||
top_p=0.95,
|
||||
do_sample=True,
|
||||
repetition_penalty=1.1,
|
||||
pad_token_id=tokenizer.eos_token_id,
|
||||
)
|
||||
|
||||
# Decode and print
|
||||
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
print(f"Prompt: {prompt}")
|
||||
print(f"Response: {response[len(prompt):].strip()}")
|
||||
|
||||
Method 2: Pipeline for Simple Inference
|
||||
from transformers import pipeline
|
||||
|
||||
pipe = pipeline(
|
||||
"text-generation",
|
||||
model="arif-butt/tinyllama-trl-merged",
|
||||
torch_dtype=torch.float16,
|
||||
device_map="auto",
|
||||
)
|
||||
|
||||
prompt = "Q: Explain neural networks in simple terms\nA:"
|
||||
result = pipe(prompt, max_new_tokens=150, temperature=0.7, do_sample=True)
|
||||
print(result[0]["generated_text"])
|
||||
|
||||
15
chat_template.jinja
Normal file
15
chat_template.jinja
Normal file
@@ -0,0 +1,15 @@
|
||||
{% for message in messages %}
|
||||
{% if message['role'] == 'user' %}
|
||||
{{ '<|user|>
|
||||
' + message['content'] + eos_token }}
|
||||
{% elif message['role'] == 'system' %}
|
||||
{{ '<|system|>
|
||||
' + message['content'] + eos_token }}
|
||||
{% elif message['role'] == 'assistant' %}
|
||||
{{ '<|assistant|>
|
||||
' + message['content'] + eos_token }}
|
||||
{% endif %}
|
||||
{% if loop.last and add_generation_prompt %}
|
||||
{{ '<|assistant|>' }}
|
||||
{% endif %}
|
||||
{% endfor %}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "float16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 5632,
|
||||
"max_position_embeddings": 2048,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 22,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": null,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 10000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "5.3.0",
|
||||
"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": "5.3.0"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2c1127d4c8d94e0a85b4b9814d6deccade3b98d70e18eb377d6fffbd45919497
|
||||
size 2200119664
|
||||
277129
tokenizer.json
Normal file
277129
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
15
tokenizer_config.json
Normal file
15
tokenizer_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"add_prefix_space": null,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"is_local": true,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "</s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user