Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 onnx/directml/mistralai_Mistral-7B-Instruct-v0.3-int4/model.onnx.data filter=lfs diff=lfs merge=lfs -text
+onnx/cpu_and_mobile/mistral-7b-instruct-v0.3-cpu-int4-rtn-block-32-acc-level-4/model.onnx.data filter=lfs diff=lfs merge=lfs -text

onnx/cpu_and_mobile/mistral-7b-instruct-v0.3-cpu-int4-rtn-block-32-acc-level-4/genai_config.json

@@ -0,0 +1,49 @@
+{
+    "model": {
+        "bos_token_id": 1,
+        "context_length": 32768,
+        "decoder": {
+            "session_options": {
+                "log_id": "onnxruntime-genai",
+                "provider_options": []
+            },
+            "filename": "model.onnx",
+            "head_size": 128,
+            "hidden_size": 4096,
+            "inputs": {
+                "input_ids": "input_ids",
+                "attention_mask": "attention_mask",
+                "past_key_names": "past_key_values.%d.key",
+                "past_value_names": "past_key_values.%d.value"
+            },
+            "outputs": {
+                "logits": "logits",
+                "present_key_names": "present.%d.key",
+                "present_value_names": "present.%d.value"
+            },
+            "num_attention_heads": 32,
+            "num_hidden_layers": 32,
+            "num_key_value_heads": 8
+        },
+        "eos_token_id": 2,
+        "pad_token_id": 2,
+        "type": "mistral",
+        "vocab_size": 32768
+    },
+    "search": {
+        "diversity_penalty": 0.0,
+        "do_sample": false,
+        "early_stopping": true,
+        "length_penalty": 1.0,
+        "max_length": 32768,
+        "min_length": 0,
+        "no_repeat_ngram_size": 0,
+        "num_beams": 1,
+        "num_return_sequences": 1,
+        "past_present_share_buffer": true,
+        "repetition_penalty": 1.0,
+        "temperature": 1.0,
+        "top_k": 1,
+        "top_p": 1.0
+    }
+}

onnx/cpu_and_mobile/mistral-7b-instruct-v0.3-cpu-int4-rtn-block-32-acc-level-4/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d32c143c394d25fc91a1eb3820d5bd02b4d894f55828ed547434eebcad773e
+size 212044

onnx/cpu_and_mobile/mistral-7b-instruct-v0.3-cpu-int4-rtn-block-32-acc-level-4/model.onnx.data

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7c99565ad875c283ee02e47cc8a80b51471b34a257db5d073a53f580da3e94
+size 5000675328

onnx/cpu_and_mobile/mistral-7b-instruct-v0.3-cpu-int4-rtn-block-32-acc-level-4/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
+  }
+}

onnx/cpu_and_mobile/mistral-7b-instruct-v0.3-cpu-int4-rtn-block-32-acc-level-4/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404