---
language:
- en
- it
library_name: transformers
base_model: DeepMount00/Llama-3.1-8b-Ita
tags:
- TensorBlock
- GGUF
model-index:
- name: Llama-3.1-8b-ITA
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: IFEval (0-Shot)
type: HuggingFaceH4/ifeval
args:
num_few_shot: 0
metrics:
- type: inst_level_strict_acc and prompt_level_strict_acc
value: 79.17
name: strict accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: BBH (3-Shot)
type: BBH
args:
num_few_shot: 3
metrics:
- type: acc_norm
value: 30.93
name: normalized accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MATH Lvl 5 (4-Shot)
type: hendrycks/competition_math
args:
num_few_shot: 4
metrics:
- type: exact_match
value: 10.88
name: exact match
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GPQA (0-shot)
type: Idavidrein/gpqa
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 5.03
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MuSR (0-shot)
type: TAUR-Lab/MuSR
args:
num_few_shot: 0
metrics:
- type: acc_norm
value: 11.4
name: acc_norm
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU-PRO (5-shot)
type: TIGER-Lab/MMLU-Pro
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 31.96
name: accuracy
source:
url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=DeepMount00/Llama-3.1-8b-ITA
name: Open LLM Leaderboard
---
## DeepMount00/Llama-3.1-8b-Ita - GGUF
This repo contains GGUF format model files for [DeepMount00/Llama-3.1-8b-Ita](https://huggingface.co/DeepMount00/Llama-3.1-8b-Ita).
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).
## Prompt template
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
```
## Model file specification
| Filename | Quant type | File Size | Description |
| -------- | ---------- | --------- | ----------- |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
| [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 |
## Downloading instruction
### Command line
Firstly, install Huggingface Client
```shell
pip install -U "huggingface_hub[cli]"
```
Then, downoad the individual model file the a local directory
```shell
huggingface-cli download tensorblock/Llama-3.1-8b-Ita-GGUF --include "Llama-3.1-8b-Ita-Q2_K.gguf" --local-dir MY_LOCAL_DIR
```
If you wanna download multiple model files with a pattern (e.g., `*Q4_K*gguf`), you can try:
```shell
huggingface-cli download tensorblock/Llama-3.1-8b-Ita-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
```