tencent_ContextPilot-14B-GGUF

Llamacpp imatrix Quantizations of ContextPilot-14B by tencent

Using llama.cpp release b10665 for quantization.

Original model: https://huggingface.co/tencent/ContextPilot-14B

Model details:

• Parameter count: 15B
• Input support: text
• Speculative decoding: no
• imatrix: yes - details

How to run

Prompt format

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Don't know which to choose? Grab Q4_K_M (9.29GB) - usually a good mix of size and performance. Download instructions available here

Available files:

Download a specific file:

hf download bartowski/tencent_ContextPilot-14B-GGUF --include "tencent_ContextPilot-14B-Q4_K_M.gguf" --local-dir ./

Downloading using the Hugging Face CLI

First, make sure you have the Hugging Face CLI installed:

pip install -U "huggingface_hub[cli]"

Download a specific file:

hf download bartowski/tencent_ContextPilot-14B-GGUF --include "tencent_ContextPilot-14B-Q4_K_M.gguf" --local-dir ./

How to run

These quants run with llama.cpp - installable in one line via llama.app:

curl -LsSf https://llama.app/install.sh | sh
llama-server -hf bartowski/tencent_ContextPilot-14B-GGUF:Q4_K_M

llama-server includes a built-in chat web UI, served at http://localhost:8080 by default.

These quants were made with llama.cpp release b10665 - if this model's architecture is newly supported, you'll need that release or newer to run them.

They also work in: LM Studio · koboldcpp · ramalama · Jan AI · Text Generation Web UI · LoLLMs · Atomic Chat

imatrix

All quants made using imatrix option, with a calibration corpus rendered through this model's own chat template. The corpus pairs plain prose with tool-calling and reasoning conversations (corpus source data), encoded exactly as this model sees them at inference and processed with --parse-special, so chat-format special tokens contribute to the importance matrix. The corpus rendered for this model is included in this repo: tencent_ContextPilot-14B-calibration-v6.txt. The imatrix is available here: tencent_ContextPilot-14B-imatrix.gguf.

{
  "generator": "auto_quant_v2 calibration renderer",
  "recipe": "calibration-v6",
  "model": "ContextPilot-14B",
  "encoder": "chat_template",
  "chunk_size": 512,
  "prose_chunks": 218,
  "tool_chunks": 299,
  "total_chunks": 517,
  "tool_chunk_fraction": 0.578,
  "n_conversations": 137,
  "extension_convs_used": 0,
  "conversation_token_lengths": [
    446,
    1498,
    764,
    1268,
    975,
    1218,
    2403,
    524,
    1084,
    1093,
    938,
    1978,
    755,
    831,
    2250,
    1105,
    999,
    867,
    617,
    597,
    1230,
    896,
    1223,
    1082,
    1600,
    1378,
    912,
    581,
    838,
    1369,
    1392,
    695,
    1125,
    918,
    1014,
    1545,
    1497,
    1060,
    359,
    1780,
    1279,
    970,
    1248,
    1645,
    1840,
    1164,
    1491,
    624,
    2276,
    977,
    2510,
    644,
    878,
    618,
    898,
    579,
    2168,
    613,
    1029,
    967,
    1077,
    1048,
    784,
    877,
    821,
    1290,
    782,
    1395,
    1713,
    718,
    321,
    982,
    2888,
    2627,
    591,
    615,
    895,
    662,
    1150,
    955,
    999,
    671,
    917,
    907,
    1167,
    1366,
    1247,
    1235,
    724,
    533,
    2311,
    629,
    1028,
    1539,
    1801,
    1084,
    509,
    1212,
    1119,
    1587,
    1565,
    1509,
    692,
    633,
    895,
    2628,
    621,
    464,
    629,
    1139,
    932,
    1250,
    650,
    349,
    317,
    2166,
    592,
    988,
    1699,
    1564,
    2208,
    2227,
    558,
    858,
    722,
    698,
    1094,
    855,
    727,
    1187,
    711,
    591,
    1286,
    885,
    799,
    1162,
    1322
  ],
  "warnings": []
}

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

ARM/AVX information

llama.cpp automatically "repacks" weights into an interleaved layout at load time for faster inference on ARM and AVX machines - details in this PR. This once required downloading special Q4_0_4_4/4_8/8_8 files; those are long gone. Online repacking now covers Q4_0, IQ4_NL, and most K-quants, so no special quant choice is needed for CPU inference.

Which file should I choose?

An older (early 2024) but still useful write-up with charts comparing quant performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Hugging Face can also do this math for you: add your hardware in your Local Apps settings and the model page will show which files fit.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

Credits

Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset.

Thank you ZeroWw for the inspiration to experiment with embed/output.

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski