Upload model Mistral-Large-Instruct-2407-v16-k65536-16384-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": 4.797906398773193,
+        "c4": 7.611056804656982,
+        "c4-new": 8.51098346710205
+    },
+    "ctx_4096": {
+        "wikitext2": 4.509005069732666,
+        "c4": 7.219871997833252,
+        "c4-new": 8.102221488952637
+    },
+    "ctx_8192": {
+        "wikitext2": 4.364211559295654,
+        "c4": 5.560217380523682,
+        "c4-new": 8.000030517578125
+    }
+}
+```

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 sha256:64b549653c4d38bd340f6399d389404bec876e297f81fccd3faaec7482bbca4c
+size 4975820720

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92f4fcb104cd877a2c02ef2ebba5915ebacf31e2c38942bd1087270823eb2566
+size 4931266016

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1ba78c567f95fa9e1a649a6f33505339d1b5af944a67e65f40d8367d1e0380
+size 4978599624

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205a35aa67655a2cf6b22f53f51134a53a42aec125274ffa4d76d9eeeab960b0
+size 4980641376

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064e72647edf422a19a258401bc402c9f0233ad0178491940a7d8205beb3523f
+size 4978599624

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c12220d65a1b0306b5536abc288d8be5bfb51c660806f14f982f50ea7d2064d
+size 4980641376

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29e0cc0fb4712f9b0bd17fb56b3cfa1b14a6425378e38b71bec4ce6631e5105b
+size 2006213536

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