add mixtral-8x7b

README.md

@@ -0,0 +1,48 @@
+# Mixtral-8x7b-Instruct-v0.1-int4-ov
+ * Model creator: [Mistral AI](https://huggingface.co/mistralai)
+ * Original model: [Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
+
+## Description
+This is [Mixtral-8x7b-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) model converted to [OpenVINO](https://docs.openvino.ai/2024/home.html) Intermediate Representation (IR) format with INT4 compressed weights using [NNCF](https://github.com/openvinotoolkit/nncf).
+
+## Compatibility
+
+This provided IR is compatible with openvino starting with 2024.0.0 version and optimum-intel 1.16.0
+
+## Usage
+
+### Install required packages
+
+To install the required components for using [Optimum Intel integration](https://huggingface.co/docs/optimum/intel/index) with the OpenVINO backend, do: 
+```
+pip install optimum[openvino]
+```
+
+### Run model inference
+```
+from transformers import AutoTokenizer
+from optimum.intel.openvino import OVModelForCausalLM
+
+model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = OVModelForCausalLM.from_pretrained(model_id)
+
+
+messages = [
+    {"role": "user", "content": "What is your favourite condiment?"},
+    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
+    {"role": "user", "content": "Do you have mayonnaise recipes?"}
+]
+
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
+
+outputs = model.generate(inputs, max_new_tokens=20)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+For more examples and possible optimizations please refer [OpenVINO Large Language Model Inference Guide](https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide.html)
+
+### Limitations
+
+Please check original model card for model usage [limitations](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1#limitations)
+

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/nfs/ov-share-05/data/cv_bench_cache/DL_benchmarking_models/mixtral-8x7b-v0.1/pytorch",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "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,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

openvino_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65631dc423958095dcacf7266918cc31423e8358cb23335bd0025d4e6515048
+size 28742920831

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.model

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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>",
+  "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
+}