Upload model Mistral-Large-Instruct-2407-v8-k65536-0-woft

README.md

@@ -0,0 +1,46 @@
+
+---
+license: other
+license_name: mrl
+license_link: https://mistral.ai/licenses/MRL-0.1.md
+base_model:
+- mistralai/Mistral-Large-Instruct-2407
+base_model_relation: quantized
+tags:
+- VPTQ
+- Quantized
+- Quantization
+---
+**Disclaimer**: 
+
+The model is reproduced based on the paper *VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models* [github](https://github.com/microsoft/vptq) and [arXiv](https://arxiv.org/abs/2409.17066)
+
+The model itself is sourced from a community release. 
+
+It is intended only for experimental purposes. 
+
+Users are responsible for any consequences arising from the use of this model.
+
+**Note**: 
+
+The PPL test results are for reference only and were collected using GPTQ testing script.
+
+```json
+{
+    "ctx_2048": {
+        "wikitext2": 4.733607292175293,
+        "c4": 7.597944736480713,
+        "c4-new": 8.575641632080078
+    },
+    "ctx_4096": {
+        "wikitext2": 4.495976448059082,
+        "c4": 7.27150297164917,
+        "c4-new": 8.283945083618164
+    },
+    "ctx_8192": {
+        "wikitext2": 4.373597621917725,
+        "c4": 5.573808670043945,
+        "c4-new": 8.310025215148926
+    }
+}
+```

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376ee1abf3b7ce04d6eb6d0bcf4d45fd8c2605cfa2856640a490124101de589b
+size 4964583776

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72b2b9191d5ef4ca3aba2b5592ce96078b615270c01547b6f9b61008e280881d
+size 4956532304

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4661a169df3b63f29000fbe64eb85c7585cb8e5851e3f1f4d58e18d0b67df591
+size 4956532304

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb9c8886e9bace9d52eff484a4acb3bc5dafa6da27b5784ba197e2f5e199c3a
+size 4956532304

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e070f50ed48b752215006d189279aadc0f0a2d612c44ddc20fe2903ee379ceb0
+size 4956532304

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f9641ebf1d3a875549910b939695b9ad63b3a1e46395f28b46dc8004255d565
+size 4956532304

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c25707272a1a0bf65850280908e48f7bac0e8568763ed949f38a6d5b5596f58
+size 3018737848

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 sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583