Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server
4yo1/llama3-pre1-pre2-inst3-lora3-mergkit-base - GGUF
This repo contains GGUF format model files for 4yo1/llama3-pre1-pre2-inst3-lora3-mergkit-base.
The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.
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 |
|---|---|---|---|
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q2_K.gguf | Q2_K | 2.980 GB | smallest, significant quality loss - not recommended for most purposes |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q3_K_S.gguf | Q3_K_S | 3.428 GB | very small, high quality loss |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q3_K_M.gguf | Q3_K_M | 3.741 GB | very small, high quality loss |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q3_K_L.gguf | Q3_K_L | 4.021 GB | small, substantial quality loss |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q4_0.gguf | Q4_0 | 4.340 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q4_K_S.gguf | Q4_K_S | 4.362 GB | small, greater quality loss |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q4_K_M.gguf | Q4_K_M | 4.566 GB | medium, balanced quality - recommended |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q5_0.gguf | Q5_0 | 5.198 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q5_K_S.gguf | Q5_K_S | 5.198 GB | large, low quality loss - recommended |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q5_K_M.gguf | Q5_K_M | 5.315 GB | large, very low quality loss - recommended |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q6_K.gguf | Q6_K | 6.110 GB | very large, extremely low quality loss |
| llama3-pre1-pre2-inst3-lora3-mergkit-base-Q8_0.gguf | Q8_0 | 7.911 GB | very large, extremely low quality loss - not recommended |
Downloading instruction
Command line
Firstly, install Huggingface Client
pip install -U "huggingface_hub[cli]"
Then, downoad the individual model file the a local directory
huggingface-cli download tensorblock/llama3-pre1-pre2-inst3-lora3-mergkit-base-GGUF --include "llama3-pre1-pre2-inst3-lora3-mergkit-base-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:
huggingface-cli download tensorblock/llama3-pre1-pre2-inst3-lora3-mergkit-base-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'
- Downloads last month
- 311
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.