YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Quantization made by Richard Erkhov.
phi_2 - GGUF
- Model creator: https://huggingface.co/EITD/
- Original model: https://huggingface.co/EITD/phi_2/
| Name | Quant method | Size |
|---|---|---|
| phi_2.Q2_K.gguf | Q2_K | 1.35GB |
| phi_2.IQ3_XS.gguf | IQ3_XS | 1.49GB |
| phi_2.IQ3_S.gguf | IQ3_S | 1.57GB |
| phi_2.Q3_K_S.gguf | Q3_K_S | 1.57GB |
| phi_2.IQ3_M.gguf | IQ3_M | 1.65GB |
| phi_2.Q3_K.gguf | Q3_K | 1.75GB |
| phi_2.Q3_K_M.gguf | Q3_K_M | 1.75GB |
| phi_2.Q3_K_L.gguf | Q3_K_L | 1.9GB |
| phi_2.IQ4_XS.gguf | IQ4_XS | 1.93GB |
| phi_2.Q4_0.gguf | Q4_0 | 2.03GB |
| phi_2.IQ4_NL.gguf | IQ4_NL | 2.04GB |
| phi_2.Q4_K_S.gguf | Q4_K_S | 2.04GB |
| phi_2.Q4_K.gguf | Q4_K | 2.16GB |
| phi_2.Q4_K_M.gguf | Q4_K_M | 2.16GB |
| phi_2.Q4_1.gguf | Q4_1 | 2.24GB |
| phi_2.Q5_0.gguf | Q5_0 | 2.46GB |
| phi_2.Q5_K_S.gguf | Q5_K_S | 2.46GB |
| phi_2.Q5_K.gguf | Q5_K | 2.53GB |
| phi_2.Q5_K_M.gguf | Q5_K_M | 2.53GB |
| phi_2.Q5_1.gguf | Q5_1 | 2.68GB |
| phi_2.Q6_K.gguf | Q6_K | 2.92GB |
| phi_2.Q8_0.gguf | Q8_0 | 3.78GB |
Original model description:
base_model: unsloth/Phi-3.5-mini-instruct tags: - text-generation-inference - transformers - unsloth - llama - trl - sft license: apache-2.0 language: - en
Uploaded model
- Developed by: EITD
- License: apache-2.0
- Finetuned from model : unsloth/Phi-3.5-mini-instruct
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 2
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support