Upload model Mistral-Large-Instruct-2407-v16-k65536-1024-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": 6.874824523925781,
+        "c4": 10.510944366455078,
+        "c4-new": 12.159836769104004
+    },
+    "ctx_4096": {
+        "wikitext2": 6.375296592712402,
+        "c4": 9.913671493530273,
+        "c4-new": 11.587206840515137
+    },
+    "ctx_8192": {
+        "wikitext2": 6.131728172302246,
+        "c4": 7.288276672363281,
+        "c4-new": 11.48729133605957
+    }
+}
+```

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-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:889b93b01c7ff3c44dbb5d10b3012f5762b99f73d5a51d6fd982ceeffe9c4fad
+size 4999759296

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cfeb733a2d2e22e57dedd80985afae49e9684bdfcf35750086c0041297cdd62
+size 4930360152

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ef93c0e9d9d024010a6570dcdb8d6986a09ce4d00e0621133c940d740183f14
+size 4970502768

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aff5282f3a63b5fa6f9edde2b4d9e078e0b3ebd95e88a7950aea749cf3547e31
+size 4970601072

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42ff3a821447da0d8ac153af97e8b9661d83e24886993fae974b38ebb895b907
+size 4999770712

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bac8cec6d7fba8de8bdd1087d71b7b432e478c4fef857bc83725a3ba9fd6b97f
+size 2851679912

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