Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- README.md +172 -0
- falcon-mamba-7b-Q2_K.gguf +3 -0
- falcon-mamba-7b-Q3_K_L.gguf +3 -0
- falcon-mamba-7b-Q3_K_M.gguf +3 -0
- falcon-mamba-7b-Q3_K_S.gguf +3 -0
- falcon-mamba-7b-Q4_0.gguf +3 -0
- falcon-mamba-7b-Q4_K_M.gguf +3 -0
- falcon-mamba-7b-Q4_K_S.gguf +3 -0
- falcon-mamba-7b-Q5_0.gguf +3 -0
- falcon-mamba-7b-Q5_K_M.gguf +3 -0
- falcon-mamba-7b-Q5_K_S.gguf +3 -0
- falcon-mamba-7b-Q6_K.gguf +3 -0
- falcon-mamba-7b-Q8_0.gguf +3 -0
.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 |
+
falcon-mamba-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
falcon-mamba-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
falcon-mamba-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
falcon-mamba-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
falcon-mamba-7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
falcon-mamba-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
falcon-mamba-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
falcon-mamba-7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
falcon-mamba-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
falcon-mamba-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
falcon-mamba-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
falcon-mamba-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
datasets:
|
5 |
+
- tiiuae/falcon-refinedweb
|
6 |
+
- HuggingFaceFW/fineweb-edu
|
7 |
+
license: other
|
8 |
+
license_name: falcon-mamba-7b-license
|
9 |
+
license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
|
10 |
+
base_model: tiiuae/falcon-mamba-7b
|
11 |
+
tags:
|
12 |
+
- TensorBlock
|
13 |
+
- GGUF
|
14 |
+
model-index:
|
15 |
+
- name: falcon-mamba-7b
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
type: text-generation
|
19 |
+
name: Text Generation
|
20 |
+
dataset:
|
21 |
+
name: IFEval (0-Shot)
|
22 |
+
type: HuggingFaceH4/ifeval
|
23 |
+
args:
|
24 |
+
num_few_shot: 0
|
25 |
+
metrics:
|
26 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
27 |
+
value: 33.36
|
28 |
+
name: strict accuracy
|
29 |
+
source:
|
30 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
|
31 |
+
name: Open LLM Leaderboard
|
32 |
+
- task:
|
33 |
+
type: text-generation
|
34 |
+
name: Text Generation
|
35 |
+
dataset:
|
36 |
+
name: BBH (3-Shot)
|
37 |
+
type: BBH
|
38 |
+
args:
|
39 |
+
num_few_shot: 3
|
40 |
+
metrics:
|
41 |
+
- type: acc_norm
|
42 |
+
value: 19.88
|
43 |
+
name: normalized accuracy
|
44 |
+
source:
|
45 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
|
46 |
+
name: Open LLM Leaderboard
|
47 |
+
- task:
|
48 |
+
type: text-generation
|
49 |
+
name: Text Generation
|
50 |
+
dataset:
|
51 |
+
name: MATH Lvl 5 (4-Shot)
|
52 |
+
type: hendrycks/competition_math
|
53 |
+
args:
|
54 |
+
num_few_shot: 4
|
55 |
+
metrics:
|
56 |
+
- type: exact_match
|
57 |
+
value: 3.63
|
58 |
+
name: exact match
|
59 |
+
source:
|
60 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
|
61 |
+
name: Open LLM Leaderboard
|
62 |
+
- task:
|
63 |
+
type: text-generation
|
64 |
+
name: Text Generation
|
65 |
+
dataset:
|
66 |
+
name: GPQA (0-shot)
|
67 |
+
type: Idavidrein/gpqa
|
68 |
+
args:
|
69 |
+
num_few_shot: 0
|
70 |
+
metrics:
|
71 |
+
- type: acc_norm
|
72 |
+
value: 8.05
|
73 |
+
name: acc_norm
|
74 |
+
source:
|
75 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
|
76 |
+
name: Open LLM Leaderboard
|
77 |
+
- task:
|
78 |
+
type: text-generation
|
79 |
+
name: Text Generation
|
80 |
+
dataset:
|
81 |
+
name: MuSR (0-shot)
|
82 |
+
type: TAUR-Lab/MuSR
|
83 |
+
args:
|
84 |
+
num_few_shot: 0
|
85 |
+
metrics:
|
86 |
+
- type: acc_norm
|
87 |
+
value: 10.86
|
88 |
+
name: acc_norm
|
89 |
+
source:
|
90 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
|
91 |
+
name: Open LLM Leaderboard
|
92 |
+
- task:
|
93 |
+
type: text-generation
|
94 |
+
name: Text Generation
|
95 |
+
dataset:
|
96 |
+
name: MMLU-PRO (5-shot)
|
97 |
+
type: TIGER-Lab/MMLU-Pro
|
98 |
+
config: main
|
99 |
+
split: test
|
100 |
+
args:
|
101 |
+
num_few_shot: 5
|
102 |
+
metrics:
|
103 |
+
- type: acc
|
104 |
+
value: 14.47
|
105 |
+
name: accuracy
|
106 |
+
source:
|
107 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/falcon-mamba-7b
|
108 |
+
name: Open LLM Leaderboard
|
109 |
+
---
|
110 |
+
|
111 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
112 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
113 |
+
</div>
|
114 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
115 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
116 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
117 |
+
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>
|
118 |
+
</p>
|
119 |
+
</div>
|
120 |
+
</div>
|
121 |
+
|
122 |
+
## tiiuae/falcon-mamba-7b - GGUF
|
123 |
+
|
124 |
+
This repo contains GGUF format model files for [tiiuae/falcon-mamba-7b](https://huggingface.co/tiiuae/falcon-mamba-7b).
|
125 |
+
|
126 |
+
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).
|
127 |
+
|
128 |
+
## Prompt template
|
129 |
+
|
130 |
+
```
|
131 |
+
|
132 |
+
```
|
133 |
+
|
134 |
+
## Model file specification
|
135 |
+
|
136 |
+
| Filename | Quant type | File Size | Description |
|
137 |
+
| -------- | ---------- | --------- | ----------- |
|
138 |
+
| [falcon-mamba-7b-Q2_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q2_K.gguf) | Q2_K | 2.389 GB | smallest, significant quality loss - not recommended for most purposes |
|
139 |
+
| [falcon-mamba-7b-Q3_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q3_K_S.gguf) | Q3_K_S | 3.050 GB | very small, high quality loss |
|
140 |
+
| [falcon-mamba-7b-Q3_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q3_K_M.gguf) | Q3_K_M | 3.050 GB | very small, high quality loss |
|
141 |
+
| [falcon-mamba-7b-Q3_K_L.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q3_K_L.gguf) | Q3_K_L | 3.050 GB | small, substantial quality loss |
|
142 |
+
| [falcon-mamba-7b-Q4_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q4_0.gguf) | Q4_0 | 3.915 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
143 |
+
| [falcon-mamba-7b-Q4_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q4_K_S.gguf) | Q4_K_S | 3.915 GB | small, greater quality loss |
|
144 |
+
| [falcon-mamba-7b-Q4_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q4_K_M.gguf) | Q4_K_M | 3.915 GB | medium, balanced quality - recommended |
|
145 |
+
| [falcon-mamba-7b-Q5_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q5_0.gguf) | Q5_0 | 4.730 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
146 |
+
| [falcon-mamba-7b-Q5_K_S.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q5_K_S.gguf) | Q5_K_S | 4.730 GB | large, low quality loss - recommended |
|
147 |
+
| [falcon-mamba-7b-Q5_K_M.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q5_K_M.gguf) | Q5_K_M | 4.730 GB | large, very low quality loss - recommended |
|
148 |
+
| [falcon-mamba-7b-Q6_K.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q6_K.gguf) | Q6_K | 5.595 GB | very large, extremely low quality loss |
|
149 |
+
| [falcon-mamba-7b-Q8_0.gguf](https://huggingface.co/tensorblock/falcon-mamba-7b-GGUF/tree/main/falcon-mamba-7b-Q8_0.gguf) | Q8_0 | 7.232 GB | very large, extremely low quality loss - not recommended |
|
150 |
+
|
151 |
+
|
152 |
+
## Downloading instruction
|
153 |
+
|
154 |
+
### Command line
|
155 |
+
|
156 |
+
Firstly, install Huggingface Client
|
157 |
+
|
158 |
+
```shell
|
159 |
+
pip install -U "huggingface_hub[cli]"
|
160 |
+
```
|
161 |
+
|
162 |
+
Then, downoad the individual model file the a local directory
|
163 |
+
|
164 |
+
```shell
|
165 |
+
huggingface-cli download tensorblock/falcon-mamba-7b-GGUF --include "falcon-mamba-7b-Q2_K.gguf" --local-dir MY_LOCAL_DIR
|
166 |
+
```
|
167 |
+
|
168 |
+
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
|
169 |
+
|
170 |
+
```shell
|
171 |
+
huggingface-cli download tensorblock/falcon-mamba-7b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
172 |
+
```
|
falcon-mamba-7b-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8325c406eda952b24c46d08c792b755486c2e1e3d7809398e34e1aabe0f4635
|
3 |
+
size 2565011200
|
falcon-mamba-7b-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfb9598415e196bd3f7a007a566ecda6a6c21423fb3947f05ed5fe48eb723044
|
3 |
+
size 3275339520
|
falcon-mamba-7b-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:611ddf623476068e97afadd9faa6a7030f065464d70d19746f62b5f6c61ca169
|
3 |
+
size 3275339520
|
falcon-mamba-7b-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1566471de457162ef3c9c379fb91bfc3a5880b4a41831741f16f8dabeaed6c4e
|
3 |
+
size 3275339520
|
falcon-mamba-7b-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88e6c41a1eb366f1405da691d41283b43b6c99b0507f750bf8a443fd24d7d1c1
|
3 |
+
size 4204230400
|
falcon-mamba-7b-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaa31dbf8058c867844df9a47f1a4834dfc413e5f9d0ce10d710904668bede7f
|
3 |
+
size 4204230400
|
falcon-mamba-7b-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3b4c9fd92701725cb511bd5b6a94a38e0e03baeae51c1212ee8254ea44b6880
|
3 |
+
size 4204230400
|
falcon-mamba-7b-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f70d60c9b92cf1e78f5aa31fdded73992461724d17470e5f2bf67b8a81ff2996
|
3 |
+
size 5078480640
|
falcon-mamba-7b-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c032f66d7c42362872b8e69789d7f8d15f89b46f1b22097bb125f7e2af5edc67
|
3 |
+
size 5078480640
|
falcon-mamba-7b-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b991276af7a5a799b17b39593373afaa75b27b685423321a87ac7459b5618d45
|
3 |
+
size 5078480640
|
falcon-mamba-7b-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7a14c58e487988aadaa1c1d078b1d41327ba89c3a3e3d54f890af65cfc8898f
|
3 |
+
size 6007371520
|
falcon-mamba-7b-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2415f0eab5cc36d3a1c930e8235448311376c18e344bda5893f78059c80f1dc
|
3 |
+
size 7765735168
|