68 lines
2.3 KiB
Markdown
68 lines
2.3 KiB
Markdown
|
---
|
||
|
|
license: apache-2.0
|
||
|
|
base_model: Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16
|
||
|
|
library_name: transformers
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
tags:
|
||
|
|
- qwen3
|
||
|
|
- qwen
|
||
|
|
- qwen3-4b
|
||
|
|
- merged
|
||
|
|
- lora
|
||
|
|
- fp16
|
||
|
|
- no-4bit
|
||
|
|
- transformers
|
||
|
|
- text-generation
|
||
|
|
- instruction-tuned
|
||
|
|
- llama-cpp
|
||
|
|
- gguf-my-repo
|
||
|
|
datasets:
|
||
|
|
- TeichAI/claude-haiku-4.5-1700x
|
||
|
|
language:
|
||
|
|
- en
|
||
|
|
---
|
||
|
|
|
||
|
|
# Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16-Q6_K-GGUF
|
||
|
|
This model was converted to GGUF format from [`Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16`](https://huggingface.co/Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16) 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/Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16) 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 Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16-Q6_K-GGUF --hf-file qwen3-2507-4b-instruct-haiku-4.5-merged-fp16-q6_k.gguf -p "The meaning to life and the universe is"
|
||
|
|
```
|
||
|
|
|
||
|
|
### Server:
|
||
|
|
```bash
|
||
|
|
llama-server --hf-repo Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16-Q6_K-GGUF --hf-file qwen3-2507-4b-instruct-haiku-4.5-merged-fp16-q6_k.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 Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16-Q6_K-GGUF --hf-file qwen3-2507-4b-instruct-haiku-4.5-merged-fp16-q6_k.gguf -p "The meaning to life and the universe is"
|
||
|
|
```
|
||
|
|
or
|
||
|
|
```
|
||
|
|
./llama-server --hf-repo Tralalabs/Qwen3-2507-4B-Instruct-Haiku-4.5-Merged-FP16-Q6_K-GGUF --hf-file qwen3-2507-4b-instruct-haiku-4.5-merged-fp16-q6_k.gguf -c 2048
|
||
|
|
```
|