Upload Qwen2ForCausalLM

config.json

@@ -1,30 +1,29 @@
 {
   "_name_or_path": "lamini_docs_100_steps/final",
   "architectures": [
-    "GPTNeoXForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": true,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "classifier_dropout": 0.1,
-  "eos_token_id": 0,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 512,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neox",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 6,
-  "rope_scaling": null,
-  "rotary_emb_base": 10000,
-  "rotary_pct": 0.25,
-  "tie_word_embeddings": false,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.44.1",
   "use_cache": true,
-  "use_parallel_residual": true,
-  "vocab_size": 50304
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
 }

generation_config.json

@@ -1,6 +1,6 @@
 {
-  "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
   "transformers_version": "4.44.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f35fd3217f6968df9728d35173cfa31113f5f258a1c79ed80c1165a82efed9
-size 281715176
+oid sha256:0c6668f7d7800c35b5ec6397c581d57f570579a7904e5ed59a03f9328b47e09e
+size 1976163472