add new model tinyllama.

add download model feature.

WebUI/configs/webuiconfig.json

@@ -411,6 +411,16 @@
         "LocalModel": {
             "LLM Model": {
                 "3B Model": {
+                    "TinyLlama-1.1B-Chat-v1.0": {
+                        "path": "models/llm/TinyLlama-1.1B-Chat-v1.0",
+                        "device": "auto",
+                        "maxmemory": 20,
+                        "cputhreads": 4,
+                        "loadbits": 16,
+                        "preset": "default",
+                        "load_type": "fastchat",
+                        "Huggingface": "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+                    },
                     "fastchat-t5-3b-v1.0": {
                         "path": "models/llm/fastchat-t5-3b-v1.0",
                         "device": "auto",

WebUI/webui_pages/model_configuration/configuration.py

@@ -144,7 +144,7 @@ def configuration_page(api: ApiRequest, is_lite: bool = False):
         download_path = st.button(
             "Download",
             use_container_width=True,
-            disabled=True
+            disabled=disabled
         )
         if download_path:
             with st.spinner(f"Model downloading..., Please do not perform any actions or refresh the page."):

__webgui_server__.py

@@ -430,19 +430,11 @@ def download_llm_model(
         hugg_path: str = Body("", description="huggingface path"),
         local_path: str = Body("", description="local path"),
     ) -> Dict:
-        # import gc
-        # from transformers import AutoModel, AutoTokenizer, AutoConfig
-        # try:
-        #     tokenizer = AutoTokenizer.from_pretrained(hugg_path)
-        #     tokenizer.save_pretrained(local_path)
-        #     config = AutoConfig.from_pretrained(hugg_path)
-        #     config.save_pretrained(local_path)
-        #     model = AutoModel.from_pretrained(hugg_path)
-        #     model.save_pretrained(local_path)
-        #     del model
-        #     gc.collect()
-        #     return {"code": 200, "msg": f'Success download LLM model {model_name} to local path {local_path}.'}
-        # except Exception as e:
+        from huggingface_hub import snapshot_download
+        try:
+            path = snapshot_download(repo_id=hugg_path, local_dir=local_path, local_dir_use_symlinks=False)
+            return {"code": 200, "msg": f'Success download LLM model {model_name} to local path {local_path}.'}
+        except Exception as e:
             return {"code": 500, "msg": f'failed to download LLM model {model_name} to local path {local_path}.'}
 
     host = FSCHAT_CONTROLLER["host"]

models/llm/TinyLlama-1.1B-Chat-v1.0/README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+datasets:
+- cerebras/SlimPajama-627B
+- bigcode/starcoderdata
+- HuggingFaceH4/ultrachat_200k
+- HuggingFaceH4/ultrafeedback_binarized
+language:
+- en
+widget:
+- text: "<|system|>\nYou are a chatbot who can help code!</s>\n<|user|>\nWrite me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.</s>\n<|assistant|>\n"
+---
+<div align="center">
+
+# TinyLlama-1.1B
+</div>
+
+https://github.com/jzhang38/TinyLlama
+
+The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 
+
+
+We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
+
+#### This Model
+This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha/edit/main/README.md)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. 
+We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4." 
+
+
+#### How to use
+You will need the transformers>=4.34
+Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
+
+```python
+# Install transformers from source - only needed for versions <= v4.34
+# pip install git+https://github.com/huggingface/transformers.git
+# pip install accelerate
+
+import torch
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
+
+# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
+messages = [
+    {
+        "role": "system",
+        "content": "You are a friendly chatbot who always responds in the style of a pirate",
+    },
+    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
+]
+prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+# <|system|>
+# You are a friendly chatbot who always responds in the style of a pirate.</s>
+# <|user|>
+# How many helicopters can a human eat in one sitting?</s>
+# <|assistant|>
+# ...
+```