Text Generation
Transformers
GGUF
English
Japanese
TensorBlock
GGUF
conversational
morriszms commited on
Commit
96d652a
·
verified ·
1 Parent(s): 3c5eff7

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,15 @@ 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
+ Llama-Primus-Merged-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Llama-Primus-Merged-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
38
+ Llama-Primus-Merged-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
39
+ Llama-Primus-Merged-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
40
+ Llama-Primus-Merged-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
41
+ Llama-Primus-Merged-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
42
+ Llama-Primus-Merged-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
43
+ Llama-Primus-Merged-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
44
+ Llama-Primus-Merged-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
45
+ Llama-Primus-Merged-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
46
+ Llama-Primus-Merged-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
47
+ Llama-Primus-Merged-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-Primus-Merged-Q2_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35c364a317d84c895dc9781edf8b834d2c506378c2a965d7464243c48e77e97c
3
+ size 3179136928
Llama-Primus-Merged-Q3_K_L.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd43fe24c7ac36df78f329a4f4d67e2d9db5db39cc0453f8962d6e2031e6c45e
3
+ size 4321961888
Llama-Primus-Merged-Q3_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da657a804d3f98bb73d4d850786c2b59606ad4ddf176d72bf057c0a2454e0172
3
+ size 4018923424
Llama-Primus-Merged-Q3_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87b58faf9b11439215adf50d58a4511d20dc2a2018e32380761641fbd4c5f150
3
+ size 3664504736
Llama-Primus-Merged-Q4_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c8e4668746327f3c66adc543deba5a2e849b5a0fc753bd1c68c233c92b1263
3
+ size 4661217184
Llama-Primus-Merged-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78089c0f09f2db51f50231cc2b2795ffe0e6ff9aa0dffd3e45da820ff63a57b6
3
+ size 4920739744
Llama-Primus-Merged-Q4_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e20881acaa9b3265fc8a80714e29feeb4ef6de5d5bcbcc0e982f50fdb0f26c2d
3
+ size 4692674464
Llama-Primus-Merged-Q5_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99c9b9b304b2a854f465861a826490f68fdf2b5f8fdb95be76ef58241c9fb9c3
3
+ size 5599299488
Llama-Primus-Merged-Q5_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6638127aa4994ed6aa741c9bcae8b481539dc65b54a745b9bdd7484ebab64b02
3
+ size 5732992928
Llama-Primus-Merged-Q5_K_S.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d455af8fb77c7c8d49e0f1f0d253afdf9b6c4bd4108771c3cbe61be75fda0d8
3
+ size 5599299488
Llama-Primus-Merged-Q6_K.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de6100c9405ef5cd12f92faf510a40568bcccd32bc1815abfea99bd3e09fd77a
3
+ size 6596011936
Llama-Primus-Merged-Q8_0.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e6766f9ea766903f93dabe920e89d4382a4cc3e855520ecd98d2a6bf89500d
3
+ size 8540776352
README.md ADDED
@@ -0,0 +1,113 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ language:
4
+ - en
5
+ - ja
6
+ base_model: trendmicro-ailab/Llama-Primus-Merged
7
+ pipeline_tag: text-generation
8
+ extra_gated_fields:
9
+ Affiliation: text
10
+ Country: country
11
+ I want to use this model for:
12
+ type: select
13
+ options:
14
+ - Research
15
+ - Commercial
16
+ - label: Other
17
+ value: other
18
+ Job title:
19
+ type: select
20
+ options:
21
+ - Student
22
+ - Research graduate
23
+ - AI researcher
24
+ - AI developer/engineer
25
+ - Cybersecurity researcher
26
+ - Reporter
27
+ - Other
28
+ geo: ip_location
29
+ library_name: transformers
30
+ datasets:
31
+ - trendmicro-ailab/Primus-Seed
32
+ - trendmicro-ailab/Primus-FineWeb
33
+ - trendmicro-ailab/Primus-Instruct
34
+ tags:
35
+ - TensorBlock
36
+ - GGUF
37
+ ---
38
+
39
+ <div style="width: auto; margin-left: auto; margin-right: auto">
40
+ <img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
41
+ </div>
42
+ <div style="display: flex; justify-content: space-between; width: 100%;">
43
+ <div style="display: flex; flex-direction: column; align-items: flex-start;">
44
+ <p style="margin-top: 0.5em; margin-bottom: 0em;">
45
+ 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>
46
+ </p>
47
+ </div>
48
+ </div>
49
+
50
+ ## trendmicro-ailab/Llama-Primus-Merged - GGUF
51
+
52
+ This repo contains GGUF format model files for [trendmicro-ailab/Llama-Primus-Merged](https://huggingface.co/trendmicro-ailab/Llama-Primus-Merged).
53
+
54
+ The files were quantized using machines provided by [TensorBlock](https://tensorblock.co/), and they are compatible with llama.cpp as of [commit b4882](https://github.com/ggml-org/llama.cpp/commit/be7c3034108473beda214fd1d7c98fd6a7a3bdf5).
55
+
56
+ <div style="text-align: left; margin: 20px 0;">
57
+ <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;">
58
+ Run them on the TensorBlock client using your local machine ↗
59
+ </a>
60
+ </div>
61
+
62
+ ## Prompt template
63
+
64
+ ```
65
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
66
+
67
+ Cutting Knowledge Date: December 2023
68
+ Today Date: 26 Jul 2024
69
+
70
+ {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
71
+
72
+ {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
73
+ ```
74
+
75
+ ## Model file specification
76
+
77
+ | Filename | Quant type | File Size | Description |
78
+ | -------- | ---------- | --------- | ----------- |
79
+ | [Llama-Primus-Merged-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q2_K.gguf) | Q2_K | 3.179 GB | smallest, significant quality loss - not recommended for most purposes |
80
+ | [Llama-Primus-Merged-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q3_K_S.gguf) | Q3_K_S | 3.665 GB | very small, high quality loss |
81
+ | [Llama-Primus-Merged-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q3_K_M.gguf) | Q3_K_M | 4.019 GB | very small, high quality loss |
82
+ | [Llama-Primus-Merged-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q3_K_L.gguf) | Q3_K_L | 4.322 GB | small, substantial quality loss |
83
+ | [Llama-Primus-Merged-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q4_0.gguf) | Q4_0 | 4.661 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
84
+ | [Llama-Primus-Merged-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q4_K_S.gguf) | Q4_K_S | 4.693 GB | small, greater quality loss |
85
+ | [Llama-Primus-Merged-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q4_K_M.gguf) | Q4_K_M | 4.921 GB | medium, balanced quality - recommended |
86
+ | [Llama-Primus-Merged-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q5_0.gguf) | Q5_0 | 5.599 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
87
+ | [Llama-Primus-Merged-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q5_K_S.gguf) | Q5_K_S | 5.599 GB | large, low quality loss - recommended |
88
+ | [Llama-Primus-Merged-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q5_K_M.gguf) | Q5_K_M | 5.733 GB | large, very low quality loss - recommended |
89
+ | [Llama-Primus-Merged-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q6_K.gguf) | Q6_K | 6.596 GB | very large, extremely low quality loss |
90
+ | [Llama-Primus-Merged-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-Primus-Merged-GGUF/blob/main/Llama-Primus-Merged-Q8_0.gguf) | Q8_0 | 8.541 GB | very large, extremely low quality loss - not recommended |
91
+
92
+
93
+ ## Downloading instruction
94
+
95
+ ### Command line
96
+
97
+ Firstly, install Huggingface Client
98
+
99
+ ```shell
100
+ pip install -U "huggingface_hub[cli]"
101
+ ```
102
+
103
+ Then, downoad the individual model file the a local directory
104
+
105
+ ```shell
106
+ huggingface-cli download tensorblock/Llama-Primus-Merged-GGUF --include "Llama-Primus-Merged-Q2_K.gguf" --local-dir MY_LOCAL_DIR
107
+ ```
108
+
109
+ If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
110
+
111
+ ```shell
112
+ huggingface-cli download tensorblock/Llama-Primus-Merged-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
113
+ ```