commit files to HF hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,25 @@
+---
+language:
+- en
+tags:
+- openvino
+---
+
+# xverse/XVERSE-7B
+
+This is the [xverse/XVERSE-7B](https://huggingface.co/xverse/XVERSE-7B) 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/xverse-XVERSE-7B-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 +1,29 @@
+{
+  "_name_or_path": "xverse/XVERSE-7B",
+  "architectures": [
+    "XverseForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "xverse/XVERSE-7B--configuration_xverse.XverseConfig",
+    "AutoModelForCausalLM": "xverse/XVERSE-7B--modeling_xverse.XverseForCausalLM"
+  },
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "is_decoder": true,
+  "max_position_embeddings": 8192,
+  "max_tokenizer_truncation": 6144,
+  "model_type": "xverse",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 1,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "vocab_size": 100534
+}

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/xverse-XVERSE-7B-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 sha256:7c085f94a5939120dd962e7dd823af93eeccca9630d4d67850ab5fc6695efcfb
+size 7313716564

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:930bbe2e4026c0d6ad252202b06f7a6f75165b544e5ccf3ae847b1f4f46a732e
+size 2105140

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<|endofknowledge|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}