初始化项目，由ModelHub XC社区提供模型

Model: DineshKasi/ai-assistant
Source: Original Platform

.gitattributes

@@ -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

README.md

@@ -0,0 +1,58 @@
+---
+base_model: microsoft/DialoGPT-medium
+library_name: transformers
+model_name: ai-assistant
+tags:
+- generated_from_trainer
+- sft
+- trl
+licence: license
+---
+
+# Model Card for ai-assistant
+
+This model is a fine-tuned version of [microsoft/DialoGPT-medium](https://huggingface.co/microsoft/DialoGPT-medium).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="DineshKasi/ai-assistant", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.0.0
+- Transformers: 5.0.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 4.8.4
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

app.py

@@ -0,0 +1,208 @@
+"""
+STEP 3 — Gradio app that uses YOUR OWN model
+=============================================
+Upload this as app.py to your Hugging Face Space.
+It loads YOUR model (dineshkasi/my-ai-assistant) — not anyone else's!
+
+Your friends visit:
+  https://huggingface.co/spaces/YOUR_USERNAME/YOUR_MODEL_NAME
+"""
+
+import torch
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+# ══════════════════════════════════════════════════════
+#  ✏️  CHANGE THESE TO YOUR OWN DETAILS
+# ══════════════════════════════════════════════════════
+HF_USERNAME = "DineshKasi"
+MODEL_NAME  = "ai-assistant"
+# ══════════════════════════════════════════════════════
+
+REPO_ID = f"{HF_USERNAME}/{MODEL_NAME}"
+
+print(f"Loading YOUR model: {REPO_ID} ...")
+tokenizer = AutoTokenizer.from_pretrained(REPO_ID)
+model     = AutoModelForCausalLM.from_pretrained(REPO_ID)
+model.eval()
+print("Model loaded!")
+
+
+def ask(question, history, temperature, max_tokens):
+    """Generate a response from YOUR model."""
+    # Build context from history (last 3 turns)
+    context = ""
+    for user_msg, bot_msg in history[-3:]:
+        context += f"<|user|>{user_msg}<|endoftext|>"
+        context += f"<|assistant|>{bot_msg}<|endoftext|>"
+
+    prompt = context + f"<|user|>{question}<|endoftext|><|assistant|>"
+
+    inputs = tokenizer.encode(prompt, return_tensors="pt")
+
+    with torch.no_grad():
+        output = model.generate(
+            inputs,
+            max_new_tokens=int(max_tokens),
+            temperature=float(temperature),
+            do_sample=True,
+            top_p=0.92,
+            repetition_penalty=1.1,
+            pad_token_id=tokenizer.eos_token_id,
+            eos_token_id=tokenizer.eos_token_id,
+        )
+
+    full_text = tokenizer.decode(output[0], skip_special_tokens=True)
+
+    # Extract only the last assistant reply
+    if "<|assistant|>" in full_text:
+        reply = full_text.split("<|assistant|>")[-1].strip()
+    else:
+        reply = full_text[len(prompt):].strip()
+
+    return reply
+
+
+# ── Gradio UI ─────────────────────────────────────────
+with gr.Blocks(
+    theme=gr.themes.Soft(primary_hue="violet"),
+    title=f"{HF_USERNAME}'s AI Assistant",
+    css="""
+    #header { text-align:center; padding: 24px 0 8px; }
+    #header h1 { font-size:2rem; font-weight:700; color:#7c3aed; margin:0; }
+    #header p  { color:#6b7280; margin:6px 0 0; }
+    .badge {
+        display:inline-block; background:#f3e8ff; color:#7c3aed;
+        border-radius:999px; padding:3px 14px; font-size:0.8rem;
+        margin:3px; font-weight:500;
+    }
+    #badges { text-align:center; margin:8px 0 18px; }
+    #model-credit {
+        text-align:center; margin-top:14px;
+        font-size:0.8rem; color:#9ca3af;
+    }
+    #model-credit a { color:#7c3aed; text-decoration:none; }
+    footer { display:none !important; }
+    """,
+) as demo:
+
+    gr.HTML(f"""
+    <div id="header">
+      <h1>🤖 {HF_USERNAME}'s AI Assistant</h1>
+      <p>Powered by <a href="https://huggingface.co/{REPO_ID}" target="_blank"
+         style="color:#7c3aed;">{REPO_ID}</a> — your very own model!</p>
+    </div>
+    <div id="badges">
+      <span class="badge">💻 Coding</span>
+      <span class="badge">🔬 Science</span>
+      <span class="badge">📐 Math</span>
+      <span class="badge">✍️ Writing</span>
+      <span class="badge">📊 Business</span>
+      <span class="badge">🌍 General</span>
+    </div>
+    """)
+
+    chatbot = gr.Chatbot(
+        label="Chat with my model",
+        bubble_full_width=False,
+        height=460,
+    )
+
+    with gr.Row():
+        txt = gr.Textbox(
+            placeholder="Ask me anything...",
+            show_label=False,
+            scale=8,
+            container=False,
+        )
+        btn = gr.Button("Send ➤", variant="primary", scale=1)
+
+    gr.Examples(
+        examples=[
+            "Write a Python function to find prime numbers",
+            "Explain how neural networks learn",
+            "What is the difference between RAM and ROM?",
+            "Help me write a professional email",
+            "What is quantum entanglement?",
+            "How does a binary search tree work?",
+        ],
+        inputs=txt,
+        label="💡 Try these",
+    )
+
+    with gr.Accordion("⚙️ Settings", open=False):
+        temperature = gr.Slider(0.1, 1.2, value=0.7, step=0.1,
+                                label="Temperature (creativity)")
+        max_tokens  = gr.Slider(64, 512, value=200, step=32,
+                                label="Max response length")
+
+    with gr.Accordion("🔌 Use this model in your project", open=False):
+        gr.Markdown(f"""
+### Load my model directly in Python
+
+```python
+pip install transformers torch
+```
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+tokenizer = AutoTokenizer.from_pretrained("{REPO_ID}")
+model     = AutoModelForCausalLM.from_pretrained("{REPO_ID}")
+
+def ask(question):
+    prompt  = f"<|user|>{{question}}<|endoftext|><|assistant|>"
+    inputs  = tokenizer.encode(prompt, return_tensors="pt")
+    with torch.no_grad():
+        output = model.generate(inputs, max_new_tokens=200,
+                                 temperature=0.7, do_sample=True,
+                                 pad_token_id=tokenizer.eos_token_id)
+    reply = tokenizer.decode(output[0], skip_special_tokens=True)
+    return reply.split("<|assistant|>")[-1].strip()
+
+print(ask("Explain machine learning in simple terms"))
+```
+
+### Via Hugging Face Inference API (no install)
+
+```python
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("{REPO_ID}")
+result = client.text_generation(
+    "<|user|>What is a neural network?<|endoftext|><|assistant|>",
+    max_new_tokens=200,
+)
+print(result)
+```
+
+> Model page: [huggingface.co/{REPO_ID}](https://huggingface.co/{REPO_ID})
+        """)
+
+    gr.HTML(f"""
+    <div id="model-credit">
+        Model: <a href="https://huggingface.co/{REPO_ID}">{REPO_ID}</a>
+        &nbsp;·&nbsp; Built by {HF_USERNAME}
+        &nbsp;·&nbsp; Hosted on Hugging Face Spaces
+    </div>
+    """)
+
+    # Wiring
+    def submit(msg, history):
+        return "", history + [[msg, None]]
+
+    def respond(history, temp, max_tok):
+        question = history[-1][0]
+        history[-1][1] = ask(question, history[:-1], temp, max_tok)
+        return history
+
+    txt.submit(submit, [txt, chatbot], [txt, chatbot], queue=False).then(
+        respond, [chatbot, temperature, max_tokens], chatbot
+    )
+    btn.click(submit, [txt, chatbot], [txt, chatbot], queue=False).then(
+        respond, [chatbot, temperature, max_tokens], chatbot
+    )
+
+demo.queue()
+demo.launch()

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}

config.json

@@ -0,0 +1,40 @@
+{
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "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": {
+    "conversational": {
+      "max_length": 1000
+    }
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "pad_token_id": 50256,
+  "transformers_version": "5.0.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9eb5184a380fdb755ae917ab03703a2b4057b8e54037b80b6437abed13f01c5
+size 1625175792

requirements.txt

@@ -0,0 +1,7 @@
+transformers>=4.38.0
+datasets>=2.18.0
+accelerate>=0.27.0
+huggingface_hub>=0.21.0
+torch>=2.0.0
+gradio>=4.0.0
+tqdm

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd115a50865c9da87775f08f6a5bf9e28b5ebc21b0b76dc208ba96181b1276d
+size 5713