Upload LlamaForCausalLM

config.json

@@ -1,29 +1,31 @@
 {
   "architectures": [
-    "Qwen2ForCausalLM"
+    "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 896,
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 4864,
-  "max_position_embeddings": 32768,
-  "max_window_layers": 24,
-  "model_type": "qwen2",
-  "num_attention_heads": 14,
+  "intermediate_size": 2048,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
   "num_hidden_layers": 24,
-  "num_key_value_heads": 2,
+  "num_key_value_heads": 16,
+  "pad_token_id": 100257,
+  "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
-  "tie_word_embeddings": true,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
+  "unsloth_version": "2025.3.19",
   "use_cache": false,
-  "use_mrope": false,
-  "use_sliding_window": false,
-  "vocab_size": 151936
+  "vocab_size": 100263
 }

generation_config.json

@@ -1,6 +1,9 @@
 {
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.51.3"
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 100257,
+  "transformers_version": "4.51.3",
+  "use_cache": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47aa3b8cb74e9fb18785789e9c666ddc91aef8626aa73cf1643b58c130230e6b
-size 988097824
+oid sha256:9890c9c94eb7ffd05a7871a498ae341666c91a7f463393eb41f90f6aaa4ed202
+size 914119032