Improve language tag

README.md

@@ -1,58 +1,68 @@
----
-license: mit
-pipeline_tag: text-generation
-language:
-- en
-- ru
-- code
-base_model:
-- Qwen/Qwen2.5-7B-Instruct
-tags:
-- qwen2.5
----
-
-### theqwenmoe
-- 18.3B parametrs
-- English & Russian
-- Math & Logic
-- Code: Python, Javascript, Java, PHP, C++, C#, ...
-
-This is experimental model. Can be bugs and various problems.
-
-Made with mergekit and unsloth apps by ehristoforu.
-
-Code usage example:
-```py
-from transformers import AutoModelForCausalLM, AutoTokenizer
-
-model_name = "ehristoforu/theqwenmoe"
-
-model = AutoModelForCausalLM.from_pretrained(
-    model_name,
-    torch_dtype="auto",
-    device_map="auto"
-)
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-prompt = "Give me a short introduction to large language model."
-messages = [
-    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
-    {"role": "user", "content": prompt}
-]
-text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True
-)
-model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
-
-generated_ids = model.generate(
-    **model_inputs,
-    max_new_tokens=512
-)
-generated_ids = [
-    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
-]
-
-response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+---
+license: mit
+pipeline_tag: text-generation
+language:
+- zho
+- eng
+- fra
+- spa
+- por
+- deu
+- ita
+- rus
+- jpn
+- kor
+- vie
+- tha
+- ara
+base_model:
+- Qwen/Qwen2.5-7B-Instruct
+tags:
+- qwen2.5
+---
+
+### theqwenmoe
+- 18.3B parametrs
+- English & Russian
+- Math & Logic
+- Code: Python, Javascript, Java, PHP, C++, C#, ...
+
+This is experimental model. Can be bugs and various problems.
+
+Made with mergekit and unsloth apps by ehristoforu.
+
+Code usage example:
+```py
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "ehristoforu/theqwenmoe"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 ```