bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 17:30:07 +08:00
commit e7453e0787
28 changed files with 317 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
.gitattributes vendored Normal file
View File

@@ -0,0 +1,59 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-0.5B-f32.gguf filter=lfs diff=lfs merge=lfs -text

3
Dolphin3.0-Qwen2.5-0.5B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9877702b90b7e89f7bb12bff62ab28211017725febf0ea0055a67779b6d1cfec
size 328600384

3
Dolphin3.0-Qwen2.5-0.5B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75b6b09ce74736d996dad6e6b31014f408a0e32033dc237055e5e8abb5a4694d
size 342755392

3
Dolphin3.0-Qwen2.5-0.5B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44698c2966f40735231a473ea9dcd727c20ecdf470f9083cbc13194034705a1d
size 338610496

3
Dolphin3.0-Qwen2.5-0.5B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:52d04ef0fd4246320c68318536df6f6583f46b3c0d80c5f56e08efd853118bc7
size 352674112

3
Dolphin3.0-Qwen2.5-0.5B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebd473333e4106586e9a74084c8b1ec8cc2ec84e79df83fd78b2c201117f114d
size 349405504

3
Dolphin3.0-Qwen2.5-0.5B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e37f48b84cda5740e5bbde7205b538cc482a290774f0fe3e4381b02515578577
size 338610496

3
Dolphin3.0-Qwen2.5-0.5B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e37f48b84cda5740e5bbde7205b538cc482a290774f0fe3e4381b02515578577
size 338610496

3
Dolphin3.0-Qwen2.5-0.5B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:91803c004159e633c3e445465b96342b338a58ad8b326d4d97fe55a36ff54138
size 369361216

3
Dolphin3.0-Qwen2.5-0.5B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0fba904f57c75c8cf2ba8d56ed39335e855678bd0569763cb4d75a9f716f253f
size 355469632

3
Dolphin3.0-Qwen2.5-0.5B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:609b376012869bc314e263fe7ba9be06337317fcbc12dd67c06a43283e03ace2
size 338266432

3
Dolphin3.0-Qwen2.5-0.5B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:91803c004159e633c3e445465b96342b338a58ad8b326d4d97fe55a36ff54138
size 369361216

3
Dolphin3.0-Qwen2.5-0.5B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4cc1307071050d40be7ef86929cefbffed498114daff9db3b324dbc3be9aedb
size 352975168

3
Dolphin3.0-Qwen2.5-0.5B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5dd3289ca27530982ed4328b94b822d70977e6e8e0750bd9a286964b5ee17fad
size 374522176

3
Dolphin3.0-Qwen2.5-0.5B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a53689e2cb91027fdc9e366142eba8e35f56c14ee353e0a4d64de981efbfffa
size 397811008

3
Dolphin3.0-Qwen2.5-0.5B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a53689e2cb91027fdc9e366142eba8e35f56c14ee353e0a4d64de981efbfffa
size 397811008

3
Dolphin3.0-Qwen2.5-0.5B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e4e71d0c652e266cf0b2a07facba1b8dc09915007082e324f54dcfe9a8f881d0
size 385474880

3
Dolphin3.0-Qwen2.5-0.5B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:368b21ab98b3370927fc0fb972eacf939284f10edf44c2a38a8aae61fd76dc44
size 420089152

3
Dolphin3.0-Qwen2.5-0.5B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:368b21ab98b3370927fc0fb972eacf939284f10edf44c2a38a8aae61fd76dc44
size 420089152

3
Dolphin3.0-Qwen2.5-0.5B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef295ad2ddf3e37430daea6c34568ff1da1b4ac251cabcff5ea99bde06c809be
size 412713280

3
Dolphin3.0-Qwen2.5-0.5B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6069d22ca52de912f4b3d466f84f68ccb005b4fe0946c002cd063788a45c0e0
size 505739584

3
Dolphin3.0-Qwen2.5-0.5B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b6069d22ca52de912f4b3d466f84f68ccb005b4fe0946c002cd063788a45c0e0
size 505739584

3
Dolphin3.0-Qwen2.5-0.5B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ecb25e3958959b169cf3f4ce3c5bbf9c975e1dd8cea0cf7fde31c2ee1b1b6d5
size 531071296

3
Dolphin3.0-Qwen2.5-0.5B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b724c27de2f26f58695dde4c609e97c08a0e503d687e7ef1dd23ff9e75bb4d60
size 994159936

3
Dolphin3.0-Qwen2.5-0.5B-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f6beb4a1c03d97c02879ee852b0873dcbdbe26cc3322183b210d6bd03f0f4213
size 1982082112

BIN
Dolphin3.0-Qwen2.5-0.5B.imatrix Normal file
View File

Binary file not shown.

185
README.md Normal file
View File

@@ -0,0 +1,185 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
language:
- en
license_link: https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE
base_model: cognitivecomputations/Dolphin3.0-Qwen2.5-0.5B
license: apache-2.0
datasets:
- OpenCoder-LLM/opc-sft-stage1
- OpenCoder-LLM/opc-sft-stage2
- microsoft/orca-agentinstruct-1M-v1
- microsoft/orca-math-word-problems-200k
- NousResearch/hermes-function-calling-v1
- AI-MO/NuminaMath-CoT
- AI-MO/NuminaMath-TIR
- allenai/tulu-3-sft-mixture
- cognitivecomputations/dolphin-coder
- HuggingFaceTB/smoltalk
- cognitivecomputations/samantha-data
- m-a-p/CodeFeedback-Filtered-Instruction
- m-a-p/Code-Feedback
---
## Llamacpp imatrix Quantizations of Dolphin3.0-Qwen2.5-0.5B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4418">b4418</a> for quantization.
Original model: https://huggingface.co/cognitivecomputations/Dolphin3.0-Qwen2.5-0.5B
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
Run them in [LM Studio](https://lmstudio.ai/)
## Prompt format
```
<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Dolphin3.0-Qwen2.5-0.5B-f32.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-f32.gguf) | f32 | 1.98GB | false | Full F32 weights. |
| [Dolphin3.0-Qwen2.5-0.5B-f16.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-f16.gguf) | f16 | 0.99GB | false | Full F16 weights. |
| [Dolphin3.0-Qwen2.5-0.5B-Q8_0.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q8_0.gguf) | Q8_0 | 0.53GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Dolphin3.0-Qwen2.5-0.5B-Q6_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q6_K_L.gguf) | Q6_K_L | 0.51GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q6_K.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q6_K.gguf) | Q6_K | 0.51GB | false | Very high quality, near perfect, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q5_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q5_K_L.gguf) | Q5_K_L | 0.42GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q5_K_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q5_K_M.gguf) | Q5_K_M | 0.42GB | false | High quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q5_K_S.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q5_K_S.gguf) | Q5_K_S | 0.41GB | false | High quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q4_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q4_K_L.gguf) | Q4_K_L | 0.40GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q4_K_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q4_K_M.gguf) | Q4_K_M | 0.40GB | false | Good quality, default size for most use cases, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q4_K_S.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q4_K_S.gguf) | Q4_K_S | 0.39GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-Q4_1.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q4_1.gguf) | Q4_1 | 0.37GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Dolphin3.0-Qwen2.5-0.5B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q3_K_XL.gguf) | Q3_K_XL | 0.37GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Dolphin3.0-Qwen2.5-0.5B-Q3_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q3_K_L.gguf) | Q3_K_L | 0.37GB | false | Lower quality but usable, good for low RAM availability. |
| [Dolphin3.0-Qwen2.5-0.5B-Q3_K_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q3_K_M.gguf) | Q3_K_M | 0.36GB | false | Low quality. |
| [Dolphin3.0-Qwen2.5-0.5B-Q4_0.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q4_0.gguf) | Q4_0 | 0.35GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Dolphin3.0-Qwen2.5-0.5B-IQ4_NL.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-IQ4_NL.gguf) | IQ4_NL | 0.35GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Dolphin3.0-Qwen2.5-0.5B-IQ4_XS.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-IQ4_XS.gguf) | IQ4_XS | 0.35GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Dolphin3.0-Qwen2.5-0.5B-IQ3_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-IQ3_M.gguf) | IQ3_M | 0.34GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Dolphin3.0-Qwen2.5-0.5B-Q3_K_S.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q3_K_S.gguf) | Q3_K_S | 0.34GB | false | Low quality, not recommended. |
| [Dolphin3.0-Qwen2.5-0.5B-IQ3_XS.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-IQ3_XS.gguf) | IQ3_XS | 0.34GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Dolphin3.0-Qwen2.5-0.5B-Q2_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q2_K_L.gguf) | Q2_K_L | 0.34GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Dolphin3.0-Qwen2.5-0.5B-Q2_K.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-Q2_K.gguf) | Q2_K | 0.34GB | false | Very low quality but surprisingly usable. |
| [Dolphin3.0-Qwen2.5-0.5B-IQ2_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-0.5B-IQ2_M.gguf) | IQ2_M | 0.33GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
## 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.
## Downloading using huggingface-cli
<details>
<summary>Click to view download instructions</summary>
First, make sure you have hugginface-cli installed:
```
pip install -U "huggingface_hub[cli]"
```
Then, you can target the specific file you want:
```
huggingface-cli download bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF --include "Dolphin3.0-Qwen2.5-0.5B-Q4_K_M.gguf" --local-dir ./
```
If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
```
huggingface-cli download bartowski/Dolphin3.0-Qwen2.5-0.5B-GGUF --include "Dolphin3.0-Qwen2.5-0.5B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Dolphin3.0-Qwen2.5-0.5B-Q8_0) or download them all in place (./)
</details>
## ARM/AVX information
Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.
Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.
As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.
Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase.
<details>
<summary>Click to view Q4_0_X_X information (deprecated</summary>
I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking.
<details>
<summary>Click to view benchmarks on an AVX2 system (EPYC7702)</summary>
| model | size | params | backend | threads | test | t/s | % (vs Q4_0) |
| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% |
| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% |
| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% |
| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% |
Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation
</details>
</details>
## Which file should I choose?
<details>
<summary>Click here for details</summary>
A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
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.
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](https://github.com/ggerganov/llama.cpp/wiki/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 and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
</details>
## 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

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}