Upload model Meta-Llama-3.1-405B-Instruct-v8-k65536-65536-woft

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,38 @@
+
+---
+license: llama3.1
+base_model:
+- meta-llama/Llama-3.1-405B-Instruct
+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": 1.9966317415237427
+    },
+    "ctx_4096": {
+        "wikitext2": 1.8661881685256958
+    },
+    "ctx_8192": {
+        "wikitext2": 1.8048142194747925
+    }
+}
+```

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "attn_implementation": "flash_attention_2",
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64bb430319d52e8f07a26f51cd1a8aaf2bcb7e4d4e9987d1c48a06a20c340d4
+size 4935192536

model-00002-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1a9a03c637dde5e50226314bb7784cccfbc438e237245857a73fa5e56ce7e1d
+size 4828487008

model-00003-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48a81667167bc915f613a35426696992088d1f7bfe6ac3d440dc8bdd48f2366
+size 4828487008

model-00004-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec0e64f4aaf25c9771ff617bbef1d49739e210d214338325e818b783d39231f
+size 4828487008

model-00005-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e7bf18a4a68ec953316528fdb52b0713fb0c53cc89c71ed6b85b08e0307a00
+size 4828487128

model-00006-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b00e374551d570ff85acf129fdd1ad38590e6ecbb00f4192635bfdf409b04d9
+size 4828487136

model-00007-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fac61068e6b91837c76fbe6c914f1497a13d90703cdf787ccaaa381727a59dfc
+size 4828487136

model-00008-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e8b7974dcfac90190760bc754ba486687236e96bd24a3fa01faf81b8aed07c4
+size 4828487136

model-00009-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:095c35d2945e5615e9e453b1b94deca83715ed96c4be0fb5d3a8bb9593a34fc1
+size 4828487136

model-00010-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f460d4b620d0d05ce57a433ee96f8167e13cf2f5e46c4c6569f4ee4f83f44b5
+size 4828487136

model-00011-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e0c4748207dbe7a730b864ed55c6335ecfc52bb835efd0afc369a7f319fe8b5
+size 4828487136

model-00012-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a983fb4f4e4033e011c6c81b442883e1426c49551a43531d3ca098d2eac3ff3
+size 4828487136

model-00013-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f859c418f726af6a757f949e8fb6f4205bbd02560e6ca4fce89afc6f221f91a6
+size 4828487136

model-00014-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ec78fd18414df686b86871ff404b305e5418e7de9cc40ca9a3b291df3d8a21d
+size 4828487136

model-00015-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40dd45dceed77b8c0020f663f1492b2f5894c0ebb4886d614c5983aa5d77591a
+size 4828487136

model-00016-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8061b14be84e109333f5b5cbff93cb4934c6b98bea88d9b850e92f2cbfc31a7a
+size 4828487136

model-00017-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b752515de1890a278626e11e078ce3533d894713d26c084d579ed7ce2504fe05
+size 4828487136

model-00018-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea30a42d78d79fd4770ae1a4e6ebc51e170cfcdc4284c6dd0e642748c45cdbe
+size 4828487136

model-00019-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a8cb39f4176a2142bf70976a484fa3568b05e4c4fbff83ce95774ae5921043
+size 4828487136

model-00020-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a2dc1ec004dfd62693511442564f2ad9e3ff1dbc48aaa4935ff9eb38e92b7f5
+size 4828487136

model-00021-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1545d0e0cced85060e4938fca8757a80edc693fb86b977d3d736dea28b6b3a7c
+size 4828487136

model-00022-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3b87e26db4fe86522a65c993e97b0d5eb036f54fa0f44f70a00bab84470525
+size 4828487136

model-00023-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:427cc7e7e9c2a23019445b7dce9d98731d0415e6ee47aea1a61c687f1b5ec9a7
+size 4828487136

model-00024-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:070eb3f3256a6361c2909786c65e7ab8fde3a91db9198233a8bf5d1058cde8dc
+size 4828487136

model-00025-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6525e0d90947a5425d96759b27404e1b4fce59415932922920bcc5daead70e
+size 4828487136

model-00026-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59dac12b3e51f0cb0843337b2b1d5465f62dacdb94b433819b81275965982dec
+size 4828487136

model-00027-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee363eb2cbdda57fff7e0779e7d0a777a816162b8ef0b6fa4b4f7b8d7d020a72
+size 4828487136

model-00028-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be91c30d7103331e9db26ad98a8c8124acd0dc5714f4283e17a6b7fe1c86693
+size 4828487136

model-00029-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd14cb918c43b2929354c99eac53cb5454b9242db059f1b1b3588c7a86c93a73
+size 4828487136

model-00030-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787b3b36d29dc542497b649588bc1ec6e6c095d8db258e2cfedbd65bb260c321
+size 4828487136

model-00031-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5c9cf4c31851fd9b257704441f2e05138c72461550819e83e753e0997376a7
+size 4828487136

model-00032-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174a7b0c25c54381e69c19227ef5bf8ea2c0bc78363df26e2cb6b4b655ab3a10
+size 4828487136

model-00033-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88ff0d10f57c7fb9355dc6737cfc8e3a1f31b5df615a72ab476c05def48afc3
+size 4828487136

model-00034-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84afaf085ed0d184036ca896cda0b8a95f29cb431ec7fedebafa30e4ea320c80
+size 4828487136

model-00035-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13544a252387c38cc6c34c4c4e8e8af7b1fd3692647972cb6523069e921a598b
+size 4828487256

model-00036-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db1ea30a1112fd84f28e3ca474efd0fc32af2febfa39fde18517532244ae3df
+size 4828487272

model-00037-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2bb141a601553026689ef0536cf50848ecfe75d1a5db4e05a1ae17d639fd05
+size 4828487272

model-00038-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b9aaaec761b0034a9567cc909e496acc4ea2dc7d5d6d62e4a6ef2b7926731d
+size 4828487272

model-00039-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3364ac3eaf1c1dc5a57b425a6cda09c430b764d6f265770a6eef3c2a0611b98e
+size 4828487272

model-00040-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab1cbf788859a7410c88dfe1ee3d77315b8934602602dd2bf4c779ef86e0db37
+size 4828487272

model-00041-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08ab0a61d0a223a546ef6d11aa2a2f58556a7e325b34a8d9d9aa8039a8384eb9
+size 4828487272

model-00042-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1393292f9e6724c0210fade389941d5687bde1491c938c1e4ad22d9a8b582640
+size 4828487272

model-00043-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f36c183e21e7b057e0473ad995943be82fd52e021eec2085308bd1d5527d1710
+size 4096020264

model-00044-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b079a02069ebe5a5f4f8135815f136afb1d6fc4423620dcb2a14fa399cdf12
+size 4202692736

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}