Upload ChatGlmForCausalLM

config.json

@@ -1,16 +1,18 @@
 {
+  "_name_or_path": "ybelkada/chatglm3-6b-hf",
+  "apply_query_key_layer_scaling": true,
   "architectures": [
     "ChatGlmForCausalLM"
-  ],  
-  "auto_map": {
-    "AutoConfig": "configuration_chatglm.ChatGLMConfig",
-    "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
-    "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
-  },
+  ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "ybelkada/chatglm3-6b-hf--configuration_chatglm.ChatGLMConfig",
+    "AutoModel": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForCausalLM": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSeq2SeqLM": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForConditionalGeneration",
+    "AutoModelForSequenceClassification": "ybelkada/chatglm3-6b-hf--modeling_chatglm.ChatGLMForSequenceClassification"
+  },
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -26,13 +28,13 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 28,
   "num_key_value_heads": 32,
+  "original_rope": true,
   "partial_rotary_factor": 0.5,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
-  "original_rope": true,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.37.0.dev0",
   "use_cache": true,
   "vocab_size": 65024

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79d92e9332b43bb6ee8241ef59df9de8d07d518ba7d7f399178787e5e2b738ac
+size 4907628040

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:028ebf86e55b1dda082ec41fc60154d2a0aea2ff6aa678469751526ff6fb0912
+size 4895090334

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be2dd590a6a19ce659170232186e6592f333e20e9614369af6acd0cf1ef2e56b
+size 2684521658

pytorch_model.bin.index.json

@@ -0,0 +1,206 @@
+{
+  "metadata": {
+    "total_size": 12487168000
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00003-of-00003.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.10.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.11.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.12.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.13.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.14.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.15.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.16.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.17.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.18.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.19.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.20.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.21.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.22.self_attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "model.layers.22.self_attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.layers.23.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.layers.24.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.layers.25.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.layers.26.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "model.layers.27.self_attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "model.layers.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "model.norm.weight": "pytorch_model-00003-of-00003.bin"
+  }
+}