Update README.md
Browse files
README.md
CHANGED
|
@@ -9,8 +9,6 @@ tags: []
|
|
| 9 |
|
| 10 |
|
| 11 |
|
| 12 |
-
## Model Details
|
| 13 |
-
|
| 14 |
### Model Description
|
| 15 |
|
| 16 |
<!-- Provide a longer summary of what this model is. -->
|
|
@@ -22,12 +20,6 @@ This is the model card of a 🤗 transformers model that has been pushed on the
|
|
| 22 |
- **Model type:** Fine-tune-DeepSeek-R1-Distill-Llama-8B
|
| 23 |
- **License:** MIT License
|
| 24 |
|
| 25 |
-
### Model Sources [optional]
|
| 26 |
-
|
| 27 |
-
|
| 28 |
-
- **Repository:** [More Information Needed]
|
| 29 |
-
- **Paper [optional]:** [More Information Needed]
|
| 30 |
-
- **Demo [optional]:** [More Information Needed]
|
| 31 |
|
| 32 |
## Uses
|
| 33 |
|
|
@@ -48,39 +40,53 @@ This model is designed for **customer support automation in the telecom industry
|
|
| 48 |
- **Developers & data scientists** fine-tuning and deploying the model.
|
| 49 |
### Direct Use
|
| 50 |
|
| 51 |
-
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 52 |
-
|
| 53 |
-
[More Information Needed]
|
| 54 |
-
|
| 55 |
-
### Downstream Use [optional]
|
| 56 |
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
[More Information Needed]
|
| 60 |
|
| 61 |
-
### Out-of-Scope Use
|
| 62 |
|
| 63 |
-
|
|
|
|
|
|
|
| 64 |
|
| 65 |
-
|
|
|
|
|
|
|
| 66 |
|
| 67 |
-
|
|
|
|
| 68 |
|
| 69 |
-
|
|
|
|
|
|
|
| 70 |
|
| 71 |
-
|
|
|
|
|
|
|
| 72 |
|
| 73 |
-
|
|
|
|
| 74 |
|
| 75 |
-
|
|
|
|
| 76 |
|
| 77 |
-
|
|
|
|
| 78 |
|
| 79 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 80 |
|
| 81 |
-
|
|
|
|
|
|
|
| 82 |
|
| 83 |
-
[More Information Needed]
|
| 84 |
|
| 85 |
## Training Details
|
| 86 |
|
|
@@ -88,26 +94,20 @@ Use the code below to get started with the model.
|
|
| 88 |
|
| 89 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 90 |
|
| 91 |
-
|
| 92 |
|
| 93 |
### Training Procedure
|
| 94 |
|
| 95 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 96 |
|
| 97 |
-
|
|
|
|
|
|
|
|
|
|
| 98 |
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
#### Training Hyperparameters
|
| 103 |
-
|
| 104 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 105 |
-
|
| 106 |
-
#### Speeds, Sizes, Times [optional]
|
| 107 |
-
|
| 108 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 109 |
-
|
| 110 |
-
[More Information Needed]
|
| 111 |
|
| 112 |
## Evaluation
|
| 113 |
|
|
@@ -141,68 +141,4 @@ Use the code below to get started with the model.
|
|
| 141 |
|
| 142 |
|
| 143 |
|
| 144 |
-
## Model Examination [optional]
|
| 145 |
-
|
| 146 |
-
<!-- Relevant interpretability work for the model goes here -->
|
| 147 |
-
|
| 148 |
-
[More Information Needed]
|
| 149 |
-
|
| 150 |
-
## Environmental Impact
|
| 151 |
-
|
| 152 |
-
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 153 |
-
|
| 154 |
-
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 155 |
-
|
| 156 |
-
- **Hardware Type:** [More Information Needed]
|
| 157 |
-
- **Hours used:** [More Information Needed]
|
| 158 |
-
- **Cloud Provider:** [More Information Needed]
|
| 159 |
-
- **Compute Region:** [More Information Needed]
|
| 160 |
-
- **Carbon Emitted:** [More Information Needed]
|
| 161 |
-
|
| 162 |
-
## Technical Specifications [optional]
|
| 163 |
-
|
| 164 |
-
### Model Architecture and Objective
|
| 165 |
-
|
| 166 |
-
[More Information Needed]
|
| 167 |
-
|
| 168 |
-
### Compute Infrastructure
|
| 169 |
-
|
| 170 |
-
[More Information Needed]
|
| 171 |
-
|
| 172 |
-
#### Hardware
|
| 173 |
-
|
| 174 |
-
[More Information Needed]
|
| 175 |
-
|
| 176 |
-
#### Software
|
| 177 |
-
|
| 178 |
-
[More Information Needed]
|
| 179 |
-
|
| 180 |
-
## Citation [optional]
|
| 181 |
-
|
| 182 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 183 |
-
|
| 184 |
-
**BibTeX:**
|
| 185 |
-
|
| 186 |
-
[More Information Needed]
|
| 187 |
-
|
| 188 |
-
**APA:**
|
| 189 |
-
|
| 190 |
-
[More Information Needed]
|
| 191 |
-
|
| 192 |
-
## Glossary [optional]
|
| 193 |
-
|
| 194 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 195 |
-
|
| 196 |
-
[More Information Needed]
|
| 197 |
-
|
| 198 |
-
## More Information [optional]
|
| 199 |
-
|
| 200 |
-
[More Information Needed]
|
| 201 |
-
|
| 202 |
-
## Model Card Authors [optional]
|
| 203 |
-
|
| 204 |
-
[More Information Needed]
|
| 205 |
-
|
| 206 |
-
## Model Card Contact
|
| 207 |
|
| 208 |
-
[More Information Needed]
|
|
|
|
| 9 |
|
| 10 |
|
| 11 |
|
|
|
|
|
|
|
| 12 |
### Model Description
|
| 13 |
|
| 14 |
<!-- Provide a longer summary of what this model is. -->
|
|
|
|
| 20 |
- **Model type:** Fine-tune-DeepSeek-R1-Distill-Llama-8B
|
| 21 |
- **License:** MIT License
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
|
| 24 |
## Uses
|
| 25 |
|
|
|
|
| 40 |
- **Developers & data scientists** fine-tuning and deploying the model.
|
| 41 |
### Direct Use
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
+
## How to Get Started with the Model
|
|
|
|
|
|
|
| 45 |
|
|
|
|
| 46 |
|
| 47 |
+
import torch
|
| 48 |
+
from unsloth import FastLanguageModel
|
| 49 |
+
from transformers import AutoTokenizer
|
| 50 |
|
| 51 |
+
# Load model and tokenizer
|
| 52 |
+
model_path = "moo100/DeepSeek-R1-telecom-chatbot"
|
| 53 |
+
model, tokenizer = FastLanguageModel.from_pretrained(model_path, max_seq_length=1024, dtype=None)
|
| 54 |
|
| 55 |
+
# Optimize for fast inference
|
| 56 |
+
model = FastLanguageModel.for_inference(model)
|
| 57 |
|
| 58 |
+
# Move model to GPU if available
|
| 59 |
+
device = "cuda" if torch.cuda.is_available() else "cpu"
|
| 60 |
+
model.to(device)
|
| 61 |
|
| 62 |
+
# Define system instruction for guided response
|
| 63 |
+
system_instruction = """You are an AI assistant. Answer user questions concisely and factually.
|
| 64 |
+
Do NOT role-play as a customer service agent. Only answer the user's query."""
|
| 65 |
|
| 66 |
+
# Define user input
|
| 67 |
+
user_input = "What are the benefits of 5G?"
|
| 68 |
|
| 69 |
+
# Construct full prompt
|
| 70 |
+
full_prompt = f"{system_instruction}\n\nUser: {user_input}\nAssistant:"
|
| 71 |
|
| 72 |
+
# Tokenize input
|
| 73 |
+
inputs = tokenizer(full_prompt, return_tensors="pt").to(device)
|
| 74 |
|
| 75 |
+
# Generate response
|
| 76 |
+
outputs = model.generate(
|
| 77 |
+
input_ids=inputs.input_ids,
|
| 78 |
+
attention_mask=inputs.attention_mask,
|
| 79 |
+
max_new_tokens=100,
|
| 80 |
+
do_sample=True,
|
| 81 |
+
temperature=0.5,
|
| 82 |
+
top_k=50,
|
| 83 |
+
eos_token_id=tokenizer.eos_token_id,
|
| 84 |
+
)
|
| 85 |
|
| 86 |
+
# Decode and print response
|
| 87 |
+
response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)
|
| 88 |
+
print(response.strip())
|
| 89 |
|
|
|
|
| 90 |
|
| 91 |
## Training Details
|
| 92 |
|
|
|
|
| 94 |
|
| 95 |
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 96 |
|
| 97 |
+
|
| 98 |
|
| 99 |
### Training Procedure
|
| 100 |
|
| 101 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 102 |
|
| 103 |
+
- **Loss Curve:** Shows a steady decline, indicating model convergence.
|
| 104 |
+
- **Learning Rate Schedule:** Linear decay applied.
|
| 105 |
+
- **Gradient Norm:** Slight increase, but under control.
|
| 106 |
+
- **Global Steps & Epochs:** Indicates training progress.
|
| 107 |
|
| 108 |
+
Below are the training metrics recorded during fine-tuning:
|
| 109 |
+
https://drive.google.com/file/d/1-SOfG8K3Qt2WSEuyj3kFhGYOYMB5Gk2r/view?usp=sharing
|
| 110 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
|
| 112 |
## Evaluation
|
| 113 |
|
|
|
|
| 141 |
|
| 142 |
|
| 143 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144 |
|
|
|