belztjti commited on
Commit
13d697b
·
verified ·
1 Parent(s): 12ebe2f

Upload folder using huggingface_hub

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "glm-4-9b-chat-1m",
3
+ "add_bias_linear": false,
4
+ "add_qkv_bias": true,
5
+ "apply_query_key_layer_scaling": true,
6
+ "apply_residual_connection_post_layernorm": false,
7
+ "architectures": [
8
+ "ChatGLMForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "attention_softmax_in_fp32": true,
12
+ "auto_map": {
13
+ "AutoConfig": "configuration_chatglm.ChatGLMConfig",
14
+ "AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
15
+ "AutoModelForCausalLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
16
+ "AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration",
17
+ "AutoModelForSequenceClassification": "modeling_chatglm.ChatGLMForSequenceClassification"
18
+ },
19
+ "bias_dropout_fusion": true,
20
+ "classifier_dropout": null,
21
+ "eos_token_id": [
22
+ 151329,
23
+ 151336,
24
+ 151338
25
+ ],
26
+ "ffn_hidden_size": 13696,
27
+ "fp32_residual_connection": false,
28
+ "hidden_dropout": 0.0,
29
+ "hidden_size": 4096,
30
+ "kv_channels": 128,
31
+ "layernorm_epsilon": 1.5625e-07,
32
+ "model_type": "chatglm",
33
+ "multi_query_attention": true,
34
+ "multi_query_group_num": 4,
35
+ "num_attention_heads": 32,
36
+ "num_hidden_layers": 40,
37
+ "num_layers": 40,
38
+ "original_rope": true,
39
+ "pad_token_id": 151329,
40
+ "padded_vocab_size": 151552,
41
+ "post_layer_norm": true,
42
+ "rmsnorm": true,
43
+ "rope_ratio": 10000,
44
+ "seq_length": 1048576,
45
+ "tie_word_embeddings": false,
46
+ "torch_dtype": "bfloat16",
47
+ "transformers_version": "4.41.2",
48
+ "use_cache": true,
49
+ "vocab_size": 151552
50
+ }
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "glm-4-9b-chat-1m",
3
  "add_bias_linear": false,
4
  "add_qkv_bias": true,
5
  "apply_query_key_layer_scaling": true,
 
1
  {
2
+ "_name_or_path": "/notebooks/glm-4-9b-chat-1m",
3
  "add_bias_linear": false,
4
  "add_qkv_bias": true,
5
  "apply_query_key_layer_scaling": true,
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a92d8069d04c287b9f982c0a64a25d8bcbbbdb95a98d258929813f642e31681
3
  size 4992537608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d126e3f07d281df85941991d2d3273e396937114b60f5e704edbf82e2b02415
3
  size 4992537608
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2eb9459791d7912384f08b32cf945b81729910d5e58bcd144705d14f256a18ef
3
  size 4978978184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6877e84d4eb06132fd9c5327931fe48a9820636e274166ed9b87fbd344142a1
3
  size 4978978184
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1edab16ea718b965884e216b1409e3c38e751e97a1433e10725eb8234dd14bb
3
  size 4945415320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33bc858d6f55744dcae6efe16c57cbc1f804781cc2dcf6ea670b08040fd1640a
3
  size 4945415320
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1cdb7cfe8373dabeee2bd1e5d43950ec1d84da81f6b48015c1b0ce47497ed8a
3
  size 4050823224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7636da3773cd04c1f27606e9d0ce04ce902798d64a4c1c9c9cfb34b065a13ed6
3
  size 4050823224