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 +1,23 @@
+---
+language:
+- en
+tags:
+- openvino
+---
+
+# mistralai/Mistral-7B-Instruct-v0.2
+
+This is the [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) model, quantized with An example of how to do inference on this model:
+```python
+from optimum.intel.openvino 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/mistralai-Mistral-7B-Instruct-v0.2-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForCausalLM.from_pretrained(model_id, revision='int8-ptq')
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+result = pipe("hello world")
+print(result)
+```
+

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "is_decoder": true,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

inference.py

@@ -0,0 +1,10 @@
+from optimum.intel.openvino 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/mistralai-Mistral-7B-Instruct-v0.2-ov"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForCausalLM.from_pretrained(model_id, revision='int8-ptq')
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+result = pipe("hello world")
+print(result)

openvino_config.json

@@ -0,0 +1,21 @@
+{
+  "compression": null,
+  "dtype": "int8",
+  "input_info": null,
+  "optimum_version": "1.18.0",
+  "quantization_config": {
+    "all_layers": null,
+    "bits": 8,
+    "dataset": null,
+    "group_size": -1,
+    "ignored_scope": null,
+    "num_samples": null,
+    "quant_method": "default",
+    "ratio": 1.0,
+    "sensitivity_metric": null,
+    "sym": false,
+    "tokenizer": null
+  },
+  "save_onnx_model": false,
+  "transformers_version": "4.37.2"
+}

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c87aaf4a0409c66efe34b90babb9b874b306e69aa28ada4d4b448dd71ee22e95
+size 7280406372

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "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:fc4f0bd70b3709312d9d1d9e5ba674794b6bc5abc17429897a540f93882f25fc
+size 1795303

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}