test

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "InternLM2ForCausalLM"
+  ],
+  "attn_implementation": "eager",
+  "auto_map": {
+    "AutoConfig": "configuration_internlm2.InternLM2Config",
+    "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
+    "AutoModel": "modeling_internlm2.InternLM2ForCausalLM"
+  },
+  "bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 32768,
+  "model_type": "internlm2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "type": "dynamic",
+    "factor": 2.0
+  },
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 92544,
+  "pretraining_tp": 1
+}

model.safetensors.index.json

@@ -0,0 +1,178 @@
+{
+  "metadata": {
+    "total_size": 3778220032
+  },
+  "weight_map": {
+    "model.layers.0.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.wo.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention.wqkv.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.attention_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.feed_forward.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.ffn_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.wo.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention.wqkv.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attention_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.feed_forward.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.tok_embeddings.weight": "model-00001-of-00002.safetensors",
+    "output.weight": "model-00002-of-00002.safetensors"
+  }
+}