初始化项目，由ModelHub XC社区提供模型

Model: duyhv1411/Llama-3.2-1B-en-vi
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 +1,49 @@
+---
+language:
+- en
+- vi
+library_name: transformers
+tags:
+- chat
+- llama
+- finetune
+- peft
+base_model: duyhv1411/Llama-3.2-1B-en-vi
+model_name: Llama-3.2-1B-en-vi
+pipeline_tag: text-generation
+inference: false
+---
+
+# duyhv1411/Llama-3.2-1B-en-vi
+
+This model is an advanced iteration of the powerful `meta-llama/Llama-3.2-1B-Instruct`, specifically fine-tuned to enhance its capabilities in generic domains.
+
+# How to use
+
+```python
+
+# Use a pipeline as a high-level helper
+
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+merged_model = AutoModelForCausalLM.from_pretrained("duyhv1411/Llama-3.2-1B-en-vi",
+        device_map="auto",
+        trust_remote_code=True,)
+tokenizer = AutoTokenizer.from_pretrained("duyhv1411/Llama-3.2-1B-en-vi")
+
+chat = [{"role": "user", "content": "Cách tính lương gross?"}]
+
+tokenized_chat = tokenizer.encode(tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True), return_tensors="pt").to(torch.device("cuda"))
+
+outputs = merged_model.generate(tokenized_chat, max_new_tokens=1024, do_sample=True, temperature = 0.9) 
+print(tokenizer.decode(outputs[0][len(tokenized_chat[0]):]))
+
+
+from transformers import pipeline
+
+chat = [{"role": "user", "content": "Cách tính lương gross?"}]
+prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True)
+
+pipe = pipeline(task="text-generation", model=merged_model, tokenizer=tokenizer, device_map="auto", return_full_text=False)
+print(pipe(prompt, max_new_tokens=1024, do_sample=True, temperature=0.9)[0]["generated_text"])
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128009,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.43.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7955a2158910657d060d9c986db67b46f5228da91b87a7edafbcf7b548b76844
+size 4943274328

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}