初始化项目，由ModelHub XC社区提供模型

Model: mnsm92/English_To_Bengali_Translation
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+tags:
+- text-generation-inference
+- text-generation
+- peft
+library_name: transformers
+base_model:
+- meta-llama/Llama-3.2-1B-Instruct
+widget:
+- messages:
+  - role: user
+    content: What is your favorite condiment?
+license: cc-by-2.0
+pipeline_tag: text-generation
+---
+
+# Model Trained Using AutoTrain
+
+This model is created from llama3.2 1B Instruct.
+email me at: nazmus.sakib.muzahid@gmail.com
+
+# Usage
+
+```python
+
+from transformers import pipeline
+import nltk
+from nltk.tokenize import sent_tokenize
+
+nltk.download("punkt_tab")
+
+pipe = pipeline("text-generation", max_new_tokens=512, do_sample=False, model="mnsm92/English_To_Bengali_Translation")
+
+def create_messages(ot: str):
+    messages = [
+
+        {
+            "role": "system",
+            "content": "Translate English to Bengali. Keep the meaning same"
+        },
+        {"role": "user", "content": ot}
+    ]
+
+    return messages
+
+text = """
+National Citizen Party (NCP) convenor Nahid Islam has said that his party will contest the upcoming 13th Jatiya Sangsad (national parliament) election in alliance with Jamaat-e-Islami and like-minded parties.
+
+However, he emphasised that there is no ideological unity between the NCP and Jamaat or its allies, describing the arrangement instead as an electoral understanding.
+
+Nahid Islam made the remarks at a press conference held at the NCP’s temporary central office in the capital’s Banglamotor area on Sunday night.
+
+Earlier in the afternoon, Jamaat-e-Islami and its like-minded parties had announced at their own press conference that the NCP would be part of their 10-party electoral understanding.
+
+Speaking at the NCP press conference, Nahid Islam outlined the background to the understanding with Jamaat and eight other parties.
+"""
+
+
+sentences = sent_tokenize(text)
+sentences = [ create_messages(sent) for sent in sentences]
+outputs = pipe(sentences, batch_size=32, truncation=True)
+output_texts = ""
+for i in outputs:
+    output_texts += i[0]['generated_text'][-1]['content']
+output_texts.replace("assistant\n\n", " ")
+
+```
+
+# Drop a feedback.

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "mnsm92/etbl-47",
+  "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": "float16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc04e4c638e6f41a270537e2cf5a58c4a3c2f044031dbc7d40b4f37eb07a90d5
+size 2471645464

runs/Jan21_19-00-29_nsr/events.out.tfevents.1737464670.nsr.11579.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7134a5fcf241905509e8fe09c61c515381a659ff7e5dca94bf3bc541cf0255ea
+size 142717

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "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": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8bc4b7876be12bdae1d76c51be2f0ed47c9a86635e4b2a10ef92637cdf05f23
+size 5496

training_params.json

@@ -0,0 +1,49 @@
+{
+    "model": "mnsm92/etbl-47",
+    "project_name": "etbl-51",
+    "data_path": "mnsm92/english_to_bengali_translation_l_part_4_09",
+    "train_split": "train",
+    "valid_split": null,
+    "add_eos_token": true,
+    "block_size": 512,
+    "model_max_length": 512,
+    "padding": "right",
+    "trainer": "sft",
+    "use_flash_attention_2": false,
+    "log": "tensorboard",
+    "disable_gradient_checkpointing": false,
+    "logging_steps": -1,
+    "eval_strategy": "epoch",
+    "save_total_limit": 1,
+    "auto_find_batch_size": false,
+    "mixed_precision": "bf16",
+    "lr": 1e-05,
+    "epochs": 1,
+    "batch_size": 8,
+    "warmup_ratio": 0.1,
+    "gradient_accumulation": 2,
+    "optimizer": "paged_adamw_8bit",
+    "scheduler": "cosine",
+    "weight_decay": 0.0,
+    "max_grad_norm": 1.0,
+    "seed": 42,
+    "chat_template": "tokenizer",
+    "quantization": "int8",
+    "target_modules": "all-linear",
+    "merge_adapter": true,
+    "peft": true,
+    "lora_r": 16,
+    "lora_alpha": 32,
+    "lora_dropout": 0.05,
+    "model_ref": null,
+    "dpo_beta": 0.1,
+    "max_prompt_length": 128,
+    "max_completion_length": 512,
+    "prompt_text_column": null,
+    "text_column": "text",
+    "rejected_text_column": null,
+    "push_to_hub": true,
+    "username": "mnsm92",
+    "unsloth": false,
+    "distributed_backend": null
+}