Upload model Mistral-Large-Instruct-2407-v16-k65536-65536-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": 4.266016960144043,
+        "c4": 7.055798530578613,
+        "c4-new": 7.898081302642822
+    },
+    "ctx_4096": {
+        "wikitext2": 4.011552333831787,
+        "c4": 6.7151970863342285,
+        "c4-new": 7.487395763397217
+    },
+    "ctx_8192": {
+        "wikitext2": 3.88692045211792,
+        "c4": 5.2052001953125,
+        "c4-new": 7.350536346435547
+    }
+}
+```

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 sha256:4e7f99a9f79ec4bc350a6eecf6aabc945839ce24439925f7681243c407a43bf8
+size 4998876008

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b683a0b58461715a6985cf3cd5de32a58234a94496b6f6de449b18477f860a2
+size 4930784992

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2787373fa6db47963ef4f677b53daa69612113f61b88651ac3dec8126ba86c35
+size 4981116632

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83a678fd52533ab2d7a31b7a8c2ad2a80bf8d15b958b3ff935cf8889051c9a37
+size 4981214936

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ebb76c7d06fd87d3cc510aa93bd7dd8f7414b895b5f1612ec95f03544dbd96b
+size 4981166032

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6767067340e0f923268da6940c4b1050b05eb3bb5fe0fa00d43e83275e520990
+size 4987631464

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bd3a6146bea29d65afab810c4932e94b774e368bc3b33faa3b26cb523cd5661
+size 4843042512

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