Upload LlamaForCausalLM

config.json

@@ -1,21 +1,24 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "_name_or_path": "meta-llama/Llama-3.2-1B",
   "architectures": [
-    "Qwen2ForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 1536,
+  "hidden_size": 2048,
   "initializer_range": 0.02,
-  "intermediate_size": 8960,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 21,
-  "model_type": "qwen2",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 28,
-  "num_key_value_heads": 2,
+  "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,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
@@ -31,14 +34,18 @@
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "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": "4.46.3",
   "use_cache": true,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 128256
 }

generation_config.json

@@ -1,14 +1,9 @@
 {
-  "bos_token_id": 151643,
+  "_from_model_config": true,
+  "bos_token_id": 128000,
   "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "pad_token_id": 151643,
-  "repetition_penalty": 1.1,
-  "temperature": 0.7,
-  "top_k": 20,
-  "top_p": 0.8,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
   "transformers_version": "4.46.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e62a0b58bfd291a9809ab89c28296b10bd6b0ad08459911abc466b1cf264058b
-size 1610369128
+oid sha256:dd42fbf9239b7b4c95edc38b191f3aea4cd745bf50fc24b5f4966d157be848e1
+size 1553151900