add transformers/dpo450

transformers/dpo450/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 3,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": true,
+  "vocab_size": 32000
+}

transformers/dpo450/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "eos_token_id": 0,
+  "pad_token_id": 1,
+  "do_sample": true,
+  "temperature": 0.8,
+  "top_p": 0.9,
+  "repetition_penalty": 1.3,
+  "max_new_tokens": 200
+}

transformers/dpo450/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42000b513a3def1c5b2b2db8705fdf2025f3cc4d634fb23ed7bf8e7e64631ab9
+size 395664320

transformers/dpo450/tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "model_max_length": 1024,
+  "bos_token": null,
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "unk_token": null,
+  "clean_up_tokenization_spaces": false,
+  "chat_template": "{% for m in messages %}{% if m['role'] == 'user' %}<|user|>{{ m['content'] }}<|assistant|>{% elif m['role'] == 'assistant' %}{{ m['content'] }}<|endoftext|>{% endif %}{% endfor %}"
+}