Upload folder using huggingface_hub
Browse files- .gitattributes +12 -0
- Llama-3.1-8b-Ita-Q2_K.gguf +3 -0
- Llama-3.1-8b-Ita-Q3_K_L.gguf +3 -0
- Llama-3.1-8b-Ita-Q3_K_M.gguf +3 -0
- Llama-3.1-8b-Ita-Q3_K_S.gguf +3 -0
- Llama-3.1-8b-Ita-Q4_0.gguf +3 -0
- Llama-3.1-8b-Ita-Q4_K_M.gguf +3 -0
- Llama-3.1-8b-Ita-Q4_K_S.gguf +3 -0
- Llama-3.1-8b-Ita-Q5_0.gguf +3 -0
- Llama-3.1-8b-Ita-Q5_K_M.gguf +3 -0
- Llama-3.1-8b-Ita-Q5_K_S.gguf +3 -0
- Llama-3.1-8b-Ita-Q6_K.gguf +3 -0
- Llama-3.1-8b-Ita-Q8_0.gguf +3 -0
- README.md +172 -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 |
+
Llama-3.1-8b-Ita-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
37 |
+
Llama-3.1-8b-Ita-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
38 |
+
Llama-3.1-8b-Ita-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
39 |
+
Llama-3.1-8b-Ita-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
40 |
+
Llama-3.1-8b-Ita-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
41 |
+
Llama-3.1-8b-Ita-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
42 |
+
Llama-3.1-8b-Ita-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
43 |
+
Llama-3.1-8b-Ita-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
|
44 |
+
Llama-3.1-8b-Ita-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
45 |
+
Llama-3.1-8b-Ita-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
46 |
+
Llama-3.1-8b-Ita-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
47 |
+
Llama-3.1-8b-Ita-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
Llama-3.1-8b-Ita-Q2_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:84183f9d60076c35179f33a3387dfa0f656160a8133de55824f160fb7d2bec52
|
3 |
+
size 3179131904
|
Llama-3.1-8b-Ita-Q3_K_L.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52699643bfe25af0d4e475014fb03ea97a321a1dfeb4be51b6ce56810aa393ff
|
3 |
+
size 4321956864
|
Llama-3.1-8b-Ita-Q3_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d85bded19c8aac437ded4977392881c5715e0a72cfcc125ee6a26e4d3fb75689
|
3 |
+
size 4018918400
|
Llama-3.1-8b-Ita-Q3_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aef28998ab63bad13f2946c16db6543c521f19ff77b98f82d3268863d5618f3e
|
3 |
+
size 3664499712
|
Llama-3.1-8b-Ita-Q4_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2256eade051ef07b546efde45c1a5156095fc57767f6c7562006b2d5ceeffbcf
|
3 |
+
size 4661212160
|
Llama-3.1-8b-Ita-Q4_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:017a923e76e6cab6f196bcd47317c726a47b3167d93f7f2947d5fec6312c1632
|
3 |
+
size 4920734720
|
Llama-3.1-8b-Ita-Q4_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f434309b1ae0e7926333ca71bafa0074c1ae6c2161b47a18e8b230696910780e
|
3 |
+
size 4692669440
|
Llama-3.1-8b-Ita-Q5_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a389d406c6796854f1be42f23ad98583ff64dc9ac620546df3c56923c5c5b9c8
|
3 |
+
size 5599294464
|
Llama-3.1-8b-Ita-Q5_K_M.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7794efc012299dc9b84de816cf7cc1ddc72241672760bd9a9f0e5002e6b6b524
|
3 |
+
size 5732987904
|
Llama-3.1-8b-Ita-Q5_K_S.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0972596b48a7db1b1a71f505bf193e43bf1340d55d63e231c2213b1c99b62f2
|
3 |
+
size 5599294464
|
Llama-3.1-8b-Ita-Q6_K.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f3d5244a336e2d21a6ddad94fe816445f315c5c8d1e753ce786b157a652ce8f
|
3 |
+
size 6596006912
|
Llama-3.1-8b-Ita-Q8_0.gguf
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28009f50a6e78af05b5b8e2e6256397d379206c3264264e09042de5f625796a0
|
3 |
+
size 8540771328
|
README.md
ADDED
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
- it
|
5 |
+
library_name: transformers
|
6 |
+
base_model: DeepMount00/Llama-3.1-8b-Ita
|
7 |
+
tags:
|
8 |
+
- TensorBlock
|
9 |
+
- GGUF
|
10 |
+
model-index:
|
11 |
+
- name: Llama-3.1-8b-ITA
|
12 |
+
results:
|
13 |
+
- task:
|
14 |
+
type: text-generation
|
15 |
+
name: Text Generation
|
16 |
+
dataset:
|
17 |
+
name: IFEval (0-Shot)
|
18 |
+
type: HuggingFaceH4/ifeval
|
19 |
+
args:
|
20 |
+
num_few_shot: 0
|
21 |
+
metrics:
|
22 |
+
- type: inst_level_strict_acc and prompt_level_strict_acc
|
23 |
+
value: 79.17
|
24 |
+
name: strict accuracy
|
25 |
+
source:
|
26 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
|
27 |
+
name: Open LLM Leaderboard
|
28 |
+
- task:
|
29 |
+
type: text-generation
|
30 |
+
name: Text Generation
|
31 |
+
dataset:
|
32 |
+
name: BBH (3-Shot)
|
33 |
+
type: BBH
|
34 |
+
args:
|
35 |
+
num_few_shot: 3
|
36 |
+
metrics:
|
37 |
+
- type: acc_norm
|
38 |
+
value: 30.93
|
39 |
+
name: normalized accuracy
|
40 |
+
source:
|
41 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
|
42 |
+
name: Open LLM Leaderboard
|
43 |
+
- task:
|
44 |
+
type: text-generation
|
45 |
+
name: Text Generation
|
46 |
+
dataset:
|
47 |
+
name: MATH Lvl 5 (4-Shot)
|
48 |
+
type: hendrycks/competition_math
|
49 |
+
args:
|
50 |
+
num_few_shot: 4
|
51 |
+
metrics:
|
52 |
+
- type: exact_match
|
53 |
+
value: 10.88
|
54 |
+
name: exact match
|
55 |
+
source:
|
56 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
|
57 |
+
name: Open LLM Leaderboard
|
58 |
+
- task:
|
59 |
+
type: text-generation
|
60 |
+
name: Text Generation
|
61 |
+
dataset:
|
62 |
+
name: GPQA (0-shot)
|
63 |
+
type: Idavidrein/gpqa
|
64 |
+
args:
|
65 |
+
num_few_shot: 0
|
66 |
+
metrics:
|
67 |
+
- type: acc_norm
|
68 |
+
value: 5.03
|
69 |
+
name: acc_norm
|
70 |
+
source:
|
71 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
|
72 |
+
name: Open LLM Leaderboard
|
73 |
+
- task:
|
74 |
+
type: text-generation
|
75 |
+
name: Text Generation
|
76 |
+
dataset:
|
77 |
+
name: MuSR (0-shot)
|
78 |
+
type: TAUR-Lab/MuSR
|
79 |
+
args:
|
80 |
+
num_few_shot: 0
|
81 |
+
metrics:
|
82 |
+
- type: acc_norm
|
83 |
+
value: 11.4
|
84 |
+
name: acc_norm
|
85 |
+
source:
|
86 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
|
87 |
+
name: Open LLM Leaderboard
|
88 |
+
- task:
|
89 |
+
type: text-generation
|
90 |
+
name: Text Generation
|
91 |
+
dataset:
|
92 |
+
name: MMLU-PRO (5-shot)
|
93 |
+
type: TIGER-Lab/MMLU-Pro
|
94 |
+
config: main
|
95 |
+
split: test
|
96 |
+
args:
|
97 |
+
num_few_shot: 5
|
98 |
+
metrics:
|
99 |
+
- type: acc
|
100 |
+
value: 31.96
|
101 |
+
name: accuracy
|
102 |
+
source:
|
103 |
+
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
|
104 |
+
name: Open LLM Leaderboard
|
105 |
+
---
|
106 |
+
|
107 |
+
<div style="width: auto; margin-left: auto; margin-right: auto">
|
108 |
+
<img src="https://i.imgur.com/jC7kdl8.jpeg" alt="TensorBlock" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
109 |
+
</div>
|
110 |
+
<div style="display: flex; justify-content: space-between; width: 100%;">
|
111 |
+
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
112 |
+
<p style="margin-top: 0.5em; margin-bottom: 0em;">
|
113 |
+
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>
|
114 |
+
</p>
|
115 |
+
</div>
|
116 |
+
</div>
|
117 |
+
|
118 |
+
## DeepMount00/Llama-3.1-8b-Ita - GGUF
|
119 |
+
|
120 |
+
This repo contains GGUF format model files for [DeepMount00/Llama-3.1-8b-Ita](https://huggingface.co/DeepMount00/Llama-3.1-8b-Ita).
|
121 |
+
|
122 |
+
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).
|
123 |
+
|
124 |
+
## Prompt template
|
125 |
+
|
126 |
+
```
|
127 |
+
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
128 |
+
|
129 |
+
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
130 |
+
|
131 |
+
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
132 |
+
```
|
133 |
+
|
134 |
+
## Model file specification
|
135 |
+
|
136 |
+
| Filename | Quant type | File Size | Description |
|
137 |
+
| -------- | ---------- | --------- | ----------- |
|
138 |
+
| [Llama-3.1-8b-Ita-Q2_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q2_K.gguf) | Q2_K | 2.961 GB | smallest, significant quality loss - not recommended for most purposes |
|
139 |
+
| [Llama-3.1-8b-Ita-Q3_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q3_K_S.gguf) | Q3_K_S | 3.413 GB | very small, high quality loss |
|
140 |
+
| [Llama-3.1-8b-Ita-Q3_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q3_K_M.gguf) | Q3_K_M | 3.743 GB | very small, high quality loss |
|
141 |
+
| [Llama-3.1-8b-Ita-Q3_K_L.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q3_K_L.gguf) | Q3_K_L | 4.025 GB | small, substantial quality loss |
|
142 |
+
| [Llama-3.1-8b-Ita-Q4_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q4_0.gguf) | Q4_0 | 4.341 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
|
143 |
+
| [Llama-3.1-8b-Ita-Q4_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q4_K_S.gguf) | Q4_K_S | 4.370 GB | small, greater quality loss |
|
144 |
+
| [Llama-3.1-8b-Ita-Q4_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q4_K_M.gguf) | Q4_K_M | 4.583 GB | medium, balanced quality - recommended |
|
145 |
+
| [Llama-3.1-8b-Ita-Q5_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q5_0.gguf) | Q5_0 | 5.215 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
|
146 |
+
| [Llama-3.1-8b-Ita-Q5_K_S.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q5_K_S.gguf) | Q5_K_S | 5.215 GB | large, low quality loss - recommended |
|
147 |
+
| [Llama-3.1-8b-Ita-Q5_K_M.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q5_K_M.gguf) | Q5_K_M | 5.339 GB | large, very low quality loss - recommended |
|
148 |
+
| [Llama-3.1-8b-Ita-Q6_K.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q6_K.gguf) | Q6_K | 6.143 GB | very large, extremely low quality loss |
|
149 |
+
| [Llama-3.1-8b-Ita-Q8_0.gguf](https://huggingface.co/tensorblock/Llama-3.1-8b-Ita-GGUF/tree/main/Llama-3.1-8b-Ita-Q8_0.gguf) | Q8_0 | 7.954 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/Llama-3.1-8b-Ita-GGUF --include "Llama-3.1-8b-Ita-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/Llama-3.1-8b-Ita-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
|
172 |
+
```
|