Upload Qwen2ForCausalLM

README.md

@@ -1,18 +1,18 @@
 ---
+base_model: Qwen/Qwen2-1.5B-Instruct
+datasets:
+- sunwu51/chinese_braille_3k_rows
+library_name: transformers
+license: other
 tags:
 - autotrain
 - text-generation-inference
 - text-generation
 - peft
-library_name: transformers
-base_model: Qwen/Qwen2-1.5B-Instruct
 widget:
-  - messages:
-      - role: user
-        content: What is your favorite condiment?
-license: other
-datasets:
-- sunwu51/chinese_braille_3k_rows
+- messages:
+  - role: user
+    content: What is your favorite condiment?
 ---
 
 # Model Trained Using AutoTrain

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "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,
+  "transformers_version": "4.41.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14061d81b674a0471acee590c5b383a09f22bed3ab18d9926f3d8cddb10eb5a
+size 3087466808