Upload LlamaForCausalLM

README.md

@@ -7,6 +7,7 @@ tags:
 - generated_from_trainer
 - llama-cpp
 - gguf-my-repo
+- llama-factory
 base_model: martimfasantos/tinyllama-1.1b-chat-dpo-full
 datasets:
 - HuggingFaceH4/ultrafeedback_binarized

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "martimfasantos/tinyllama-1.1b-chat-dpo-full",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b9e027fedc2d3de070ef6c1880e3459f1551d0b2ee5ddc44e4efd791f2e217d
+size 4400216536