Upload Qwen2ForCausalLM

README.md

@@ -22,9 +22,9 @@ model-index:
       name: QASC
       type: allenai/qasc
     metrics:
-      - name: Accuracy
-        type: accuracy
-        value: 0.98
+    - type: accuracy
+      value: 0.98
+      name: Accuracy
 ---
 
 # ECE-PRYMMAL-0.5B-FT-V4-MUSR-ENSEMBLE-Mathis

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "./mon_modele",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 131072,
+  "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_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.46.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f29e92b6376f8cadddd58ef8887488ecb53f96bb6c6c3f828015c6cbb5c08fc
+size 1976163472