|
|
--- |
|
|
base_model: OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23 |
|
|
datasets: |
|
|
- OpenLLM-Ro/ro_sft_alpaca |
|
|
- OpenLLM-Ro/ro_sft_alpaca_gpt4 |
|
|
- OpenLLM-Ro/ro_sft_dolly |
|
|
- OpenLLM-Ro/ro_sft_selfinstruct_gpt4 |
|
|
- OpenLLM-Ro/ro_sft_norobots |
|
|
- OpenLLM-Ro/ro_sft_orca |
|
|
- OpenLLM-Ro/ro_sft_camel |
|
|
- OpenLLM-Ro/ro_sft_oasst |
|
|
- OpenLLM-Ro/ro_sft_ultrachat |
|
|
- OpenLLM-Ro/ro_sft_magpie_mt |
|
|
- OpenLLM-Ro/ro_sft_magpie_reasoning |
|
|
language: |
|
|
- ro |
|
|
license: cc-by-nc-4.0 |
|
|
tags: |
|
|
- llama-cpp |
|
|
- gguf-my-repo |
|
|
model-index: |
|
|
- name: OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23 |
|
|
results: |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: RoMT-Bench |
|
|
type: RoMT-Bench |
|
|
metrics: |
|
|
- type: Score |
|
|
value: 6.43 |
|
|
name: Score |
|
|
- type: Score |
|
|
value: 6.78 |
|
|
name: First turn |
|
|
- type: Score |
|
|
value: 6.09 |
|
|
name: Second turn |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: RoCulturaBench |
|
|
type: RoCulturaBench |
|
|
metrics: |
|
|
- type: Score |
|
|
value: 4.28 |
|
|
name: Score |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: Romanian_Academic_Benchmarks |
|
|
type: Romanian_Academic_Benchmarks |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 53.36 |
|
|
name: Average accuracy |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: OpenLLM-Ro/ro_arc_challenge |
|
|
type: OpenLLM-Ro/ro_arc_challenge |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 48.97 |
|
|
name: Average accuracy |
|
|
- type: accuracy |
|
|
value: 45.24 |
|
|
name: 0-shot |
|
|
- type: accuracy |
|
|
value: 47.67 |
|
|
name: 1-shot |
|
|
- type: accuracy |
|
|
value: 49.36 |
|
|
name: 3-shot |
|
|
- type: accuracy |
|
|
value: 50.13 |
|
|
name: 5-shot |
|
|
- type: accuracy |
|
|
value: 50.81 |
|
|
name: 10-shot |
|
|
- type: accuracy |
|
|
value: 50.64 |
|
|
name: 25-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: OpenLLM-Ro/ro_mmlu |
|
|
type: OpenLLM-Ro/ro_mmlu |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 55.17 |
|
|
name: Average accuracy |
|
|
- type: accuracy |
|
|
value: 54.23 |
|
|
name: 0-shot |
|
|
- type: accuracy |
|
|
value: 56.36 |
|
|
name: 1-shot |
|
|
- type: accuracy |
|
|
value: 55.34 |
|
|
name: 3-shot |
|
|
- type: accuracy |
|
|
value: 54.74 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: OpenLLM-Ro/ro_winogrande |
|
|
type: OpenLLM-Ro/ro_winogrande |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 66.52 |
|
|
name: Average accuracy |
|
|
- type: accuracy |
|
|
value: 64.96 |
|
|
name: 0-shot |
|
|
- type: accuracy |
|
|
value: 66.77 |
|
|
name: 1-shot |
|
|
- type: accuracy |
|
|
value: 67.09 |
|
|
name: 3-shot |
|
|
- type: accuracy |
|
|
value: 67.25 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: OpenLLM-Ro/ro_hellaswag |
|
|
type: OpenLLM-Ro/ro_hellaswag |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 60.73 |
|
|
name: Average accuracy |
|
|
- type: accuracy |
|
|
value: 59.72 |
|
|
name: 0-shot |
|
|
- type: accuracy |
|
|
value: 60.3 |
|
|
name: 1-shot |
|
|
- type: accuracy |
|
|
value: 60.87 |
|
|
name: 3-shot |
|
|
- type: accuracy |
|
|
value: 61.14 |
|
|
name: 5-shot |
|
|
- type: accuracy |
|
|
value: 61.63 |
|
|
name: 10-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: OpenLLM-Ro/ro_gsm8k |
|
|
type: OpenLLM-Ro/ro_gsm8k |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 42.03 |
|
|
name: Average accuracy |
|
|
- type: accuracy |
|
|
value: 30.86 |
|
|
name: 1-shot |
|
|
- type: accuracy |
|
|
value: 43.9 |
|
|
name: 3-shot |
|
|
- type: accuracy |
|
|
value: 51.33 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: OpenLLM-Ro/ro_truthfulqa |
|
|
type: OpenLLM-Ro/ro_truthfulqa |
|
|
metrics: |
|
|
- type: accuracy |
|
|
value: 46.71 |
|
|
name: Average accuracy |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: LaRoSeDa_binary |
|
|
type: LaRoSeDa_binary |
|
|
metrics: |
|
|
- type: macro-f1 |
|
|
value: 95.32 |
|
|
name: Average macro-f1 |
|
|
- type: macro-f1 |
|
|
value: 90.97 |
|
|
name: 0-shot |
|
|
- type: macro-f1 |
|
|
value: 95.53 |
|
|
name: 1-shot |
|
|
- type: macro-f1 |
|
|
value: 97.1 |
|
|
name: 3-shot |
|
|
- type: macro-f1 |
|
|
value: 97.67 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: LaRoSeDa_multiclass |
|
|
type: LaRoSeDa_multiclass |
|
|
metrics: |
|
|
- type: macro-f1 |
|
|
value: 60.84 |
|
|
name: Average macro-f1 |
|
|
- type: macro-f1 |
|
|
value: 63.2 |
|
|
name: 0-shot |
|
|
- type: macro-f1 |
|
|
value: 64.47 |
|
|
name: 1-shot |
|
|
- type: macro-f1 |
|
|
value: 55.88 |
|
|
name: 3-shot |
|
|
- type: macro-f1 |
|
|
value: 59.8 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: WMT_EN-RO |
|
|
type: WMT_EN-RO |
|
|
metrics: |
|
|
- type: bleu |
|
|
value: 23.18 |
|
|
name: Average bleu |
|
|
- type: bleu |
|
|
value: 4.92 |
|
|
name: 0-shot |
|
|
- type: bleu |
|
|
value: 28.01 |
|
|
name: 1-shot |
|
|
- type: bleu |
|
|
value: 30.16 |
|
|
name: 3-shot |
|
|
- type: bleu |
|
|
value: 29.61 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: WMT_RO-EN |
|
|
type: WMT_RO-EN |
|
|
metrics: |
|
|
- type: bleu |
|
|
value: 25.11 |
|
|
name: Average bleu |
|
|
- type: bleu |
|
|
value: 1.43 |
|
|
name: 0-shot |
|
|
- type: bleu |
|
|
value: 24.78 |
|
|
name: 1-shot |
|
|
- type: bleu |
|
|
value: 37.31 |
|
|
name: 3-shot |
|
|
- type: bleu |
|
|
value: 36.93 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: XQuAD |
|
|
type: XQuAD |
|
|
metrics: |
|
|
- type: exact_match |
|
|
value: 10.74 |
|
|
name: Average exact_match |
|
|
- type: f1 |
|
|
value: 19.75 |
|
|
name: Average f1 |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: STS |
|
|
type: STS |
|
|
metrics: |
|
|
- type: spearman |
|
|
value: 73.53 |
|
|
name: Average spearman |
|
|
- type: pearson |
|
|
value: 74.93 |
|
|
name: Average pearson |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: XQuAD_EM |
|
|
type: XQuAD_EM |
|
|
metrics: |
|
|
- type: exact_match |
|
|
value: 11.18 |
|
|
name: 0-shot |
|
|
- type: exact_match |
|
|
value: 26.47 |
|
|
name: 1-shot |
|
|
- type: exact_match |
|
|
value: 3.95 |
|
|
name: 3-shot |
|
|
- type: exact_match |
|
|
value: 1.34 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: XQuAD_F1 |
|
|
type: XQuAD_F1 |
|
|
metrics: |
|
|
- type: f1 |
|
|
value: 25.76 |
|
|
name: 0-shot |
|
|
- type: f1 |
|
|
value: 39.25 |
|
|
name: 1-shot |
|
|
- type: f1 |
|
|
value: 8.4 |
|
|
name: 3-shot |
|
|
- type: f1 |
|
|
value: 5.58 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: STS_Spearman |
|
|
type: STS_Spearman |
|
|
metrics: |
|
|
- type: spearman |
|
|
value: 73.52 |
|
|
name: 1-shot |
|
|
- type: spearman |
|
|
value: 74.02 |
|
|
name: 3-shot |
|
|
- type: spearman |
|
|
value: 73.06 |
|
|
name: 5-shot |
|
|
- task: |
|
|
type: text-generation |
|
|
dataset: |
|
|
name: STS_Pearson |
|
|
type: STS_Pearson |
|
|
metrics: |
|
|
- type: pearson |
|
|
value: 75.81 |
|
|
name: 1-shot |
|
|
- type: pearson |
|
|
value: 74.54 |
|
|
name: 3-shot |
|
|
- type: pearson |
|
|
value: 74.43 |
|
|
name: 5-shot |
|
|
--- |
|
|
|
|
|
# LinigDrake2875/RoLlama3.1-8b-Instruct-2025-04-23-Q4_K_M-GGUF |
|
|
This model was converted to GGUF format from [`OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23`](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. |
|
|
Refer to the [original model card](https://huggingface.co/OpenLLM-Ro/RoLlama3.1-8b-Instruct-2025-04-23) for more details on the model. |
|
|
|
|
|
## Use with llama.cpp |
|
|
Install llama.cpp through brew (works on Mac and Linux) |
|
|
|
|
|
```bash |
|
|
brew install llama.cpp |
|
|
|
|
|
``` |
|
|
Invoke the llama.cpp server or the CLI. |
|
|
|
|
|
### CLI: |
|
|
```bash |
|
|
llama-cli --hf-repo LinigDrake2875/RoLlama3.1-8b-Instruct-2025-04-23-Q4_K_M-GGUF --hf-file rollama3.1-8b-instruct-2025-04-23-q4_k_m.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
|
|
|
### Server: |
|
|
```bash |
|
|
llama-server --hf-repo LinigDrake2875/RoLlama3.1-8b-Instruct-2025-04-23-Q4_K_M-GGUF --hf-file rollama3.1-8b-instruct-2025-04-23-q4_k_m.gguf -c 2048 |
|
|
``` |
|
|
|
|
|
Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. |
|
|
|
|
|
Step 1: Clone llama.cpp from GitHub. |
|
|
``` |
|
|
git clone https://github.com/ggerganov/llama.cpp |
|
|
``` |
|
|
|
|
|
Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux). |
|
|
``` |
|
|
cd llama.cpp && LLAMA_CURL=1 make |
|
|
``` |
|
|
|
|
|
Step 3: Run inference through the main binary. |
|
|
``` |
|
|
./llama-cli --hf-repo LinigDrake2875/RoLlama3.1-8b-Instruct-2025-04-23-Q4_K_M-GGUF --hf-file rollama3.1-8b-instruct-2025-04-23-q4_k_m.gguf -p "The meaning to life and the universe is" |
|
|
``` |
|
|
or |
|
|
``` |
|
|
./llama-server --hf-repo LinigDrake2875/RoLlama3.1-8b-Instruct-2025-04-23-Q4_K_M-GGUF --hf-file rollama3.1-8b-instruct-2025-04-23-q4_k_m.gguf -c 2048 |
|
|
``` |
|
|
|
