upload Baichuan models

README.md

@@ -3,14 +3,16 @@ license: mit
 language: en
 tags:
 - LLM
-- Baichuan-7B
-- Baichuan-13B-base
-- Baichuan-13B-chat
-- Baichuan2-7B-base
-- Baichuan2-13B-base
-- Baichuan2-7B-chat
-- Baichuan2-13B-chat
+- baichuan
 ---
+## Special Notes
+
+We have released **7 Baichuan models of lyra version** including Baichuan-7B, Baichuan-13B-Base, Baichuan-13B-Chat, Baichuan2-7B-Base, Baichuan2-7B-Chat, Baichuan2-13B-Base and Baichuan2-13B-Chat. 
+
+These highly optimized Baichuan models are suitable for Ampere (A100/A10) as well as Volta (V100).
+
+If you like our work and consider to join us, feel free to drop a line at benbinwu@tencent.com.
+
 ## Model Card for lyraBaichuan
 
 lyraBaichuan is currently the **fastest Baichuan models** (Baichuan-7B, Baichuan-13B, Baichuan2-7B, Baichuan2-13B) available. The inference speed of lyraBaichuan has achieved up to **4300+ tokens/s** on A100, up to **2.4x** acceleration upon the torch version.
@@ -22,6 +24,8 @@ Among its main features are:
 
 We use the Baichuan2-7B-Base and Baichuan2-13B-Base model for measurement, but this optimized inference is also applicable to other Baichuan models, including Baichuan-7B and Baichuan-13B.
 
+We already 
+
 ## Speed
 
 * Evaluated at tokens/s

models/Baichuan-13B-Base-lyra/1-gpu-fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e245813be16016ff8650562cecf38d4da489a03aaa70fa70bd337f77dc608af
+size 26529802240

models/Baichuan-13B-Base-lyra/config.ini

@@ -0,0 +1,14 @@
+[baichuan]
+model_name = Baichuan_13B_base
+head_num = 40
+size_per_head = 128
+inter_size = 13696
+num_layer = 40
+rotary_embedding = 128
+layernorm_eps = 1e-06
+vocab_size = 64000
+start_id = 1
+end_id = 2
+tensor_para_size = 1
+weight_data_type = fp16
+

models/Baichuan-13B-Base-lyra/config.json

@@ -0,0 +1,28 @@
+{
+  "_from_model_config": true,
+  "architectures": [
+    "BaichuanForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_baichuan.BaichuanConfig",
+    "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "model_max_length": 4096,
+  "model_type": "baichuan",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

models/Baichuan-13B-Base-lyra/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

models/Baichuan-13B-Base-lyra/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d1ab69d25c74644af5c5e4dcd1cc6e96d33783dbd257b6bdea55b643c72813
+size 1136765

models/Baichuan-13B-Base-lyra/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_baichuan.BaichuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "model_max_length": 4096,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BaichuanTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

models/Baichuan-13B-Chat-lyra/1-gpu-fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543d19789cfb1c11dc7b7002c0422ca69ef3f75fd6b70aefebacac232e1fcea4
+size 26529802240

models/Baichuan-13B-Chat-lyra/config.ini

@@ -0,0 +1,14 @@
+[baichuan]
+model_name = Baichuan_13B_chat
+head_num = 40
+size_per_head = 128
+inter_size = 13696
+num_layer = 40
+rotary_embedding = 128
+layernorm_eps = 1e-06
+vocab_size = 64000
+start_id = 1
+end_id = 2
+tensor_para_size = 1
+weight_data_type = fp16
+

models/Baichuan-13B-Chat-lyra/config.json

@@ -0,0 +1,28 @@
+{
+  "_from_model_config": true,
+  "_name_or_path": "baichuan-inc/Baichuan-13B-Chat",
+  "architectures": [
+    "BaichuanForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_baichuan.BaichuanConfig",
+    "AutoModelForCausalLM": "modeling_baichuan.BaichuanForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13696,
+  "model_max_length": 4096,
+  "model_type": "baichuan",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 64000
+}

models/Baichuan-13B-Chat-lyra/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

models/Baichuan-13B-Chat-lyra/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7d1ab69d25c74644af5c5e4dcd1cc6e96d33783dbd257b6bdea55b643c72813
+size 1136765

models/Baichuan-13B-Chat-lyra/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_baichuan.BaichuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "model_max_length": 4096,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BaichuanTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

models/Baichuan-7B-lyra/1-gpu-fp16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4ff9e052a29342b91cf4f0f0ef305ae72a6cf62ca8a35c0d0c367c2d8e296b
+size 14001119232

models/Baichuan-7B-lyra/config.ini

@@ -0,0 +1,14 @@
+[baichuan]
+model_name = Baichuan_7B
+head_num = 32
+size_per_head = 128
+inter_size = 11008
+num_layer = 32
+rotary_embedding = 128
+layernorm_eps = 1e-06
+vocab_size = 64000
+start_id = 1
+end_id = 2
+tensor_para_size = 1
+weight_data_type = fp16
+

models/Baichuan-7B-lyra/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BaiChuanForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_baichuan.BaiChuanConfig",
+    "AutoModelForCausalLM": "modeling_baichuan.BaiChuanForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "baichuan",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.1",
+  "use_cache": true,
+  "vocab_size": 64000
+}

models/Baichuan-7B-lyra/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

models/Baichuan-7B-lyra/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4be54af290d93c113bcbf421115ae9eed9d6340408f564898f1e966dc738ef01
+size 1136699

models/Baichuan-7B-lyra/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "auto_map": {
+    "AutoTokenizer": ["tokenization_baichuan.BaiChuanTokenizer", null]
+  },
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BaiChuanTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}