morriszms commited on
Commit
aedfb12
·
verified ·
1 Parent(s): 8a944d9

Upload folder using huggingface_hub

Browse files
Llama-3.1-8B-Instruct-Q2_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e864b710260e7421e316b307425a56c60342a59b31ec588fc59341881ef4774f
3
- size 3179131648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0761cd93b7b73d39141ce797baeb75fcceb483bfac94416e41987dd6ce8b0eb9
3
+ size 3179135808
Llama-3.1-8B-Instruct-Q3_K_L.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9000ba4a1cfd4c042152940a2133b1aabe456ee6962b85113a3f01c581d748b
3
- size 4321956608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89e23efae45d95219d133b0c7d2e8618884a628ec14b5a1f379e788e63bbe48
3
+ size 4321960768
Llama-3.1-8B-Instruct-Q3_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c7812477a1c6d55486f03ee4bed95cdbf7f092d70f9785c473dbf8a4364330f
3
- size 4018918144
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83c4ab6078f005a6ba6e46d3ed6b1cb34bf50d7a1f3cca2e34edade34cd186c5
3
+ size 4018922304
Llama-3.1-8B-Instruct-Q3_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:87bafe08ae18abdd439a93ee2b37ada9cc29ce5fcd3cb0339d974c4945712a4c
3
- size 3664499456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023edad24bdcec360d59c4c214c1af8aba5ca31fb610f1f3197003e628cbc258
3
+ size 3664503616
Llama-3.1-8B-Instruct-Q4_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0949c080b2d4460e59f72e3b2fece66b5ccc214921f99491f0f2081a4b711cd3
3
- size 4661211904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eaeed46f46e12102980669303ecec762bf3d9f5ffdc075a5023e7e56d4d91cf
3
+ size 4661216064
Llama-3.1-8B-Instruct-Q4_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa3c92662ceaa9cb90ac931411174f6bb83dbddd9e4daa36ca3f6e3a0f3c0ade
3
- size 4920734464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67587dbf666ed15718e3e7c6c640446c0b1617ce28890c29ef5e3f03866fe710
3
+ size 4920738624
Llama-3.1-8B-Instruct-Q4_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2266c79579b808ea9e73995dddb856635f95066bc3b516709b450f1cba5f5f92
3
- size 4692669184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd4499e57300eff2c0031bab43edf36c53f9d26e6468cd563aa860266ee892e
3
+ size 4692673344
Llama-3.1-8B-Instruct-Q5_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7921c2afb891bec4240c7b3153c9c16cc9d7015319d3561cec35aaa0f1a98189
3
- size 5599294208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a6a8b2bbbcbd226dc8e4e064809c74d81288e3f603a5ee50d8d39e25f549346
3
+ size 5599298368
Llama-3.1-8B-Instruct-Q5_K_M.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:013da6995eadc2ab4995028528035dd996aba8d14a5cda23a95ef306b7463716
3
- size 5732987648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7fed85ba8e2f851f2c16c27c064fa238de9adee35271ce9a7d2e0ff0d143b0f
3
+ size 5732991808
Llama-3.1-8B-Instruct-Q5_K_S.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b493058348b7a4ff68b02cb35a815fd39ae0f0f61fcce60fe354470cac7e1519
3
- size 5599294208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0935e678fa927cc5ee3f0a51a2975116493b731920dbf4c0a2e45b42a71f1cd4
3
+ size 5599298368
Llama-3.1-8B-Instruct-Q6_K.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0c67135ffdc4aa6c1bf038366b314049885fd025a4ca12b78ff85a075026083
3
- size 6596006656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:896a0f94e546bbb4ed00c9dabe84984edab07874e657de91fffa3f27ec07e7b4
3
+ size 6596010816
Llama-3.1-8B-Instruct-Q8_0.gguf CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59111ab623caeb09b72fac81653c1bbe161d80ae646247861ccd8959510e8e16
3
- size 8540771072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376d9187e1d61c936a977702901dcdd77ef6e1a0a240b96d601cff0166aab6ee
3
+ size 8540775232
README.md CHANGED
@@ -1,9 +1,8 @@
1
  ---
2
- library_name: transformers
3
  tags:
4
  - TensorBlock
5
  - GGUF
6
- base_model: phamtungthuy/Llama-3.1-8B-Instruct
7
  ---
8
 
9
  <div style="width: auto; margin-left: auto; margin-right: auto">
@@ -17,9 +16,9 @@ base_model: phamtungthuy/Llama-3.1-8B-Instruct
17
  </div>
18
  </div>
19
 
20
- ## phamtungthuy/Llama-3.1-8B-Instruct - GGUF
21
 
22
- This repo contains GGUF format model files for [phamtungthuy/Llama-3.1-8B-Instruct](https://huggingface.co/phamtungthuy/Llama-3.1-8B-Instruct).
23
 
24
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
25
 
@@ -34,6 +33,9 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
34
  ```
35
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
36
 
 
 
 
37
  {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
38
 
39
  {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
@@ -44,7 +46,7 @@ The files were quantized using machines provided by [TensorBlock](https://tensor
44
  | Filename | Quant type | File Size | Description |
45
  | -------- | ---------- | --------- | ----------- |
46
  | [Llama-3.1-8B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
47
- | [Llama-3.1-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.664 GB | very small, high quality loss |
48
  | [Llama-3.1-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
49
  | [Llama-3.1-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
50
  | [Llama-3.1-8B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
 
1
  ---
2
+ base_model: FILM6912/Llama-3.1-8B-Instruct
3
  tags:
4
  - TensorBlock
5
  - GGUF
 
6
  ---
7
 
8
  <div style="width: auto; margin-left: auto; margin-right: auto">
 
16
  </div>
17
  </div>
18
 
19
+ ## FILM6912/Llama-3.1-8B-Instruct - GGUF
20
 
21
+ This repo contains GGUF format model files for [FILM6912/Llama-3.1-8B-Instruct](https://huggingface.co/FILM6912/Llama-3.1-8B-Instruct).
22
 
23
  The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4011](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
24
 
 
33
  ```
34
  <|begin_of_text|><|start_header_id|>system<|end_header_id|>
35
 
36
+ Cutting Knowledge Date: December 2023
37
+ Today Date: 26 Jul 2024
38
+
39
  {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
40
 
41
  {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
 
46
  | Filename | Quant type | File Size | Description |
47
  | -------- | ---------- | --------- | ----------- |
48
  | [Llama-3.1-8B-Instruct-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
49
+ | [Llama-3.1-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
50
  | [Llama-3.1-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
51
  | [Llama-3.1-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
52
  | [Llama-3.1-8B-Instruct-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8B-Instruct-GGUF/blob/main/Llama-3.1-8B-Instruct-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |