Files
THaLLE-0.1-7B-fa-GGUF/README.md
ModelHub XC d49f3cd7a2 初始化项目,由ModelHub XC社区提供模型
Model: KBTG-Labs/THaLLE-0.1-7B-fa-GGUF
Source: Original Platform
2026-05-21 18:16:15 +08:00

66 lines
1.9 KiB
Markdown

---
base_model: KBTG-Labs/THaLLE-0.1-7B-fa
language:
- en
license: apache-2.0
pipeline_tag: text-generation
tags:
- finance
- llama-cpp
---
# KBTG-Labs/THaLLE-0.1-7B-fa-GGUF
This model was converted to GGUF format from [`KBTG-Labs/THaLLE-0.1-7B-fa`](https://huggingface.co/KBTG-Labs/THaLLE-0.1-7B-fa) using llama.cpp.
Refer to the [original model card](https://huggingface.co/KBTG-Labs/THaLLE-0.1-7B-fa) 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 with your perfered quantization level ("q2_k", "q3_k_m", "q4_k_m", "q5_k_m", "q6_k", "q8_0", "f16").
Smaller quantization is faster and use less memory, but will be less accurate.
### CLI:
```bash
llama-cli --hf-repo KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-<QUANTIZATION_LEVEL>.gguf -p "The meaning to life and the universe is"
```
### Server:
```bash
llama-server --hf-repo KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-<QUANTIZATION_LEVEL>.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 KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-<QUANTIZATION_LEVEL>.gguf -p "The meaning to life and the universe is"
```
or
```
./llama-server --hf-repo KBTG-Labs/THaLLE-0.1-7B-fa-GGUF --hf-file thalle-0.1-7b-fa-<QUANTIZATION_LEVEL>.gguf -c 2048
```