commit files to HF hub

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- en
+tags:
+- openvino
+---
+
+# baichuan-inc/Baichuan2-13B-Chat
+
+This is the [baichuan-inc/Baichuan2-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat) model converted to [OpenVINO](https://openvino.ai) with INT8 weights compression for accelerated inference.
+
+An example of how to do inference on this model:
+```python
+from optimum.intel import OVModelForCausalLM
+from transformers import AutoTokenizer, pipeline
+
+# model_id should be set to either a local directory or a model available on the HuggingFace hub.
+model_id = "helenai/baichuan-inc-Baichuan2-13B-Chat-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = OVModelForCausalLM.from_pretrained(model_id)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+result = pipe("hello world")
+print(result)
+```
+

config.json

@@ -0,0 +1,34 @@
+{
+  "_from_model_config": true,
+  "_name_or_path": "baichuan-inc/Baichuan2-13B-Chat",
+  "architectures": [
+    "BaichuanForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "baichuan-inc/Baichuan2-13B-Chat--configuration_baichuan.BaichuanConfig",
+    "AutoModelForCausalLM": "baichuan-inc/Baichuan2-13B-Chat--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,
+  "is_decoder": true,
+  "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,
+  "tokenizer_class": "BaichuanTokenizer",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0",
+  "use_cache": true,
+  "vocab_size": 125696,
+  "z_loss_weight": 0
+}

inference.py

@@ -0,0 +1,10 @@
+from optimum.intel import OVModelForCausalLM
+from transformers import AutoTokenizer, pipeline
+
+# model_id should be set to either a local directory or a model available on the HuggingFace hub.
+model_id = "helenai/baichuan-inc-Baichuan2-13B-Chat-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = OVModelForCausalLM.from_pretrained(model_id)
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+result = pipe("hello world")
+print(result)

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25cb2ae0f6439944e7432d7441e49253ed7f106a8fc3832a40a9d02107bfdc10
+size 16589380381

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
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": true
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79452955be6b419a65984273a9f08af86042e1c2a75ee3ba989cbf620a133cc2
+size 2001107

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": true,
+      "special": true
+    }
+  },
+  "auto_map": {
+    "AutoTokenizer": [
+      "baichuan-inc/Baichuan2-13B-Chat--tokenization_baichuan.BaichuanTokenizer",
+      null
+    ]
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "BaichuanTokenizer",
+  "unk_token": "<unk>"
+}