morriszms commited on
Commit
bf282f2
·
verified ·
1 Parent(s): da8f22a

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,18 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ CodeLlama-70b-hf-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ CodeLlama-70b-hf-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ CodeLlama-70b-hf-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ CodeLlama-70b-hf-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ CodeLlama-70b-hf-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ CodeLlama-70b-hf-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ CodeLlama-70b-hf-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ CodeLlama-70b-hf-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ CodeLlama-70b-hf-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ CodeLlama-70b-hf-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ CodeLlama-70b-hf-Q6_K/CodeLlama-70b-hf-Q6_K-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
47
+ CodeLlama-70b-hf-Q6_K/CodeLlama-70b-hf-Q6_K-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
48
+ CodeLlama-70b-hf-Q8_0/CodeLlama-70b-hf-Q8_0-00001-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
49
+ CodeLlama-70b-hf-Q8_0/CodeLlama-70b-hf-Q8_0-00002-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
50
+ CodeLlama-70b-hf-Q8_0/CodeLlama-70b-hf-Q8_0-00003-of-00003.gguf filter=lfs diff=lfs merge=lfs -text
CodeLlama-70b-hf-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d285fcccc24f35af81aa9f1dd3488ac55042b24d713ab44bd2e17e544a35737
3
+ size 25462588320
CodeLlama-70b-hf-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:441bcaa4673915b5efbbb6ab54f11f13aa1006c9ea71181d82c38091f0a77c2a
3
+ size 36148000672
CodeLlama-70b-hf-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76ff7d81d310a576edad6ce85df8ae0c2bdf1acd1ee9c1c77d2d928d79e9379f
3
+ size 33274902432
CodeLlama-70b-hf-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50fbf7d210d3ff025fa57a0b4baef3f84326f82ba15c92de05a3a730a86024b8
3
+ size 29919459232
CodeLlama-70b-hf-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ebc4799906106a8acbe237e0217fad4b079dc21027c1f50034d4d2e26fc80f6
3
+ size 38872431520
CodeLlama-70b-hf-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fee28ca15501425b3363030aade527f982aded3b6d028089db9b72a38db9f18a
3
+ size 41423092640
CodeLlama-70b-hf-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63bcf6d18d62f586fc53109500491ead0fae227fa3a1abe243c43f7e28c990fd
3
+ size 39249918880
CodeLlama-70b-hf-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f70d3778f9a197740d04c8c69c8cef24adeff4dddbb5ed44043049f17ab68861
3
+ size 47461596064
CodeLlama-70b-hf-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08034965c513305cd5ebc4c89d3c9fc899b12d85be244162ab8d0ef2661a2392
3
+ size 48753965984
CodeLlama-70b-hf-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67cb85b2be0ce430a6459efdff9c93f0203bfe92d9cce2168d58ebab82deb344
3
+ size 47461596064
CodeLlama-70b-hf-Q6_K/CodeLlama-70b-hf-Q6_K-00001-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38c2c64ace3004db291b81f64c564959db6c1621eb2f1f2ac944318aad74ad0
3
+ size 34950823904
CodeLlama-70b-hf-Q6_K/CodeLlama-70b-hf-Q6_K-00002-of-00002.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62a5a3aa1683f6fe8a5fc3c381a649806b52f95210fca6dd899bd5d1ea11b31e
3
+ size 21636759680
CodeLlama-70b-hf-Q8_0/CodeLlama-70b-hf-Q8_0-00001-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce3cb5e2b5e463a11208ef0e5c10ed9b8801a0451fd90e1e02aedd0e5c612c27
3
+ size 34857426784
CodeLlama-70b-hf-Q8_0/CodeLlama-70b-hf-Q8_0-00002-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42d6ba18ef7d4af2dbaa959c2be7db5b93d7556db3be50613cb7452d3c7703cf
3
+ size 34958922176
CodeLlama-70b-hf-Q8_0/CodeLlama-70b-hf-Q8_0-00003-of-00003.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:649a2210775e623e954375725df2b3304ebb641d4a6e17ddfe28c99599858b48
3
+ size 3476260800
README.md ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - code
4
+ pipeline_tag: text-generation
5
+ tags:
6
+ - llama-2
7
+ - TensorBlock
8
+ - GGUF
9
+ license: llama2
10
+ base_model: codellama/CodeLlama-70b-hf
11
+ ---
12
+
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <div style="display: flex; justify-content: space-between; width: 100%;">
17
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
18
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
19
+ Feedback and support: TensorBlock's <a href="https://x.com/tensorblock_aoi">Twitter/X</a>, <a href="https://t.me/TensorBlock">Telegram Group</a> and <a href="https://x.com/tensorblock_aoi">Discord server</a>
20
+ </p>
21
+ </div>
22
+ </div>
23
+
24
+ ## codellama/CodeLlama-70b-hf - GGUF
25
+
26
+ This repo contains GGUF format model files for [codellama/CodeLlama-70b-hf](https://huggingface.co/codellama/CodeLlama-70b-hf).
27
+
28
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4242](https://github.com/ggerganov/llama.cpp/commit/a6744e43e80f4be6398fc7733a01642c846dce1d).
29
+
30
+ <div style="text-align: left; margin: 20px 0;">
31
+ <a href="https://tensorblock.co/waitlist/client" style="display: inline-block; padding: 10px 20px; background-color: #007bff; color: white; text-decoration: none; border-radius: 5px; font-weight: bold;">
32
+ Run them on the TensorBlock client using your local machine ↗
33
+ </a>
34
+ </div>
35
+
36
+ ## Prompt template
37
+
38
+ ```
39
+
40
+ ```
41
+
42
+ ## Model file specification
43
+
44
+ | Filename | Quant type | File Size | Description |
45
+ | -------- | ---------- | --------- | ----------- |
46
+ | [CodeLlama-70b-hf-Q2_K.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q2_K.gguf) | Q2_K | 25.463 GB | smallest, significant quality loss - not recommended for most purposes |
47
+ | [CodeLlama-70b-hf-Q3_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q3_K_S.gguf) | Q3_K_S | 29.919 GB | very small, high quality loss |
48
+ | [CodeLlama-70b-hf-Q3_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q3_K_M.gguf) | Q3_K_M | 33.275 GB | very small, high quality loss |
49
+ | [CodeLlama-70b-hf-Q3_K_L.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q3_K_L.gguf) | Q3_K_L | 36.148 GB | small, substantial quality loss |
50
+ | [CodeLlama-70b-hf-Q4_0.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q4_0.gguf) | Q4_0 | 38.872 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
51
+ | [CodeLlama-70b-hf-Q4_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q4_K_S.gguf) | Q4_K_S | 39.250 GB | small, greater quality loss |
52
+ | [CodeLlama-70b-hf-Q4_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q4_K_M.gguf) | Q4_K_M | 41.423 GB | medium, balanced quality - recommended |
53
+ | [CodeLlama-70b-hf-Q5_0.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q5_0.gguf) | Q5_0 | 47.462 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
54
+ | [CodeLlama-70b-hf-Q5_K_S.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q5_K_S.gguf) | Q5_K_S | 47.462 GB | large, low quality loss - recommended |
55
+ | [CodeLlama-70b-hf-Q5_K_M.gguf](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q5_K_M.gguf) | Q5_K_M | 48.754 GB | large, very low quality loss - recommended |
56
+ | [CodeLlama-70b-hf-Q6_K](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q6_K) | Q6_K | 56.588 GB | very large, extremely low quality loss |
57
+ | [CodeLlama-70b-hf-Q8_0](https://huggingface.co/tensorblock/CodeLlama-70b-hf-GGUF/blob/main/CodeLlama-70b-hf-Q8_0) | Q8_0 | 73.293 GB | very large, extremely low quality loss - not recommended |
58
+
59
+
60
+ ## Downloading instruction
61
+
62
+ ### Command line
63
+
64
+ Firstly, install Huggingface Client
65
+
66
+ ```shell
67
+ pip install -U "huggingface_hub[cli]"
68
+ ```
69
+
70
+ Then, downoad the individual model file the a local directory
71
+
72
+ ```shell
73
+ huggingface-cli download tensorblock/CodeLlama-70b-hf-GGUF --include "CodeLlama-70b-hf-Q2_K.gguf" --local-dir MY_LOCAL_DIR
74
+ ```
75
+
76
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
77
+
78
+ ```shell
79
+ huggingface-cli download tensorblock/CodeLlama-70b-hf-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
80
+ ```