Add doc

README.md

@@ -0,0 +1,77 @@
+---
+license: apache-2.0
+language: fr
+pipeline_tag: text-generation
+inference:
+  parameters:
+    temperature: 0.7
+tags:
+- LLM
+- finetuned
+---
+
+# Vigogne-Stablelm-3B-4E1T-Chat
+
+An attempt to fine-tune the [stablelm-3b-4e1t](https://huggingface.co/stabilityai/stablelm-3b-4e1t) model to explore the feasibility of adapting a "smaller-scale" language model, primarily pretrained on English datasets, for French chat.
+
+**License**: A significant portion of the training data is distilled from GPT-3.5-Turbo and GPT-4, kindly use it cautiously to avoid any violations of OpenAI's [terms of use](https://openai.com/policies/terms-of-use).
+
+## Usage
+
+```python
+from typing import Dict, List, Optional
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, TextStreamer
+
+model_name_or_path = "bofenghuang/vigogne-stablelm-3b-4e1t-chat"
+tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)
+
+streamer = TextStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+
+
+def chat(
+    query: str,
+    history: Optional[List[Dict]] = None,
+    temperature: float = 0.7,
+    top_p: float = 1.0,
+    top_k: float = 0,
+    repetition_penalty: float = 1.1,
+    max_new_tokens: int = 1024,
+    **kwargs,
+):
+    if history is None:
+        history = []
+
+    history.append({"role": "user", "content": query})
+
+    input_ids = tokenizer.apply_chat_template(history, return_tensors="pt").to(model.device)
+    input_length = input_ids.shape[1]
+
+    generated_outputs = model.generate(
+        input_ids=input_ids,
+        generation_config=GenerationConfig(
+            temperature=temperature,
+            do_sample=temperature > 0.0,
+            top_p=top_p,
+            top_k=top_k,
+            repetition_penalty=repetition_penalty,
+            max_new_tokens=max_new_tokens,
+            pad_token_id=tokenizer.eos_token_id,
+            **kwargs,
+        ),
+        streamer=streamer,
+        return_dict_in_generate=True,
+    )
+
+    generated_tokens = generated_outputs.sequences[0, input_length:]
+    generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
+
+    history.append({"role": "assistant", "content": generated_text})
+
+    return generated_text, history
+
+
+# 1st round
+response, history = chat("Un escargot parcourt 100 mètres en 5 heures. Quelle est sa vitesse ?", history=None)
+```