bartowski/Dolphin3.0-Qwen2.5-1.5B-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-Qwen2.5-1.5B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-18 07:00:14 +08:00
commit 8818fd77af
28 changed files with 321 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
.gitattributes vendored Normal file
View File

@@ -0,0 +1,60 @@
*.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-Qwen2.5-1.5B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B-f32.gguf filter=lfs diff=lfs merge=lfs -text
Dolphin3.0-Qwen2.5-1.5B.imatrix filter=lfs diff=lfs merge=lfs -text

3
Dolphin3.0-Qwen2.5-1.5B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0ad6d010065604031d0a182f7001e1b31c781e01f323a38de93700f882ea028b
size 601057856

3
Dolphin3.0-Qwen2.5-1.5B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ecd2cc54fea65dfba24300109dcba64c5aa2d1a2f80f0d99a035259a0ede9bd1
size 776667200

3
Dolphin3.0-Qwen2.5-1.5B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:875204a0ff123f76956ca4e035dd35b72b88fcafebf9501ec6814738087050a9
size 731702336

3
Dolphin3.0-Qwen2.5-1.5B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e211d10c84aeb977388d9674ac227032a2e1e8cf4482fbcbb4ae6cd1884c09f
size 936334400

3
Dolphin3.0-Qwen2.5-1.5B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:248e459e292304eaea9947628af229c5daa6817832a35e317aa34eabc3231c6f
size 895734848

3
Dolphin3.0-Qwen2.5-1.5B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5d1c9170c4a28df46e5193ff049a93e9704d32bfb2a8b4972d3824b6ed7175e6
size 676308032

3
Dolphin3.0-Qwen2.5-1.5B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9b129d5627542b945742772d21fdc583936684bfff54b09909a1a8233ba841ff
size 732828224

3
Dolphin3.0-Qwen2.5-1.5B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c332f437decf1d295469857a1e855f6d0bdeffae17fdc8b1c5d9e89d0b71e8fe
size 880165952

3
Dolphin3.0-Qwen2.5-1.5B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc637ccc69dacc6057e10da0e99b63f544b4f658d3d437b691e9c875f2c8393a
size 824181824

3
Dolphin3.0-Qwen2.5-1.5B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97479a91629096469405cffb80661d91139bc2866c8bd0ee86cdad5ccacd67f8
size 760947776

3
Dolphin3.0-Qwen2.5-1.5B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bc7da68bd4bdfb5ed07dd4f743aa055934d8faf8aeff7a4f4c22c94e9b1ab04f
size 936686144

3
Dolphin3.0-Qwen2.5-1.5B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d9dc778f039abe533706081a11373c4f3eda3a5cb86f7b579eb3e37726ccc50
size 937538624

3
Dolphin3.0-Qwen2.5-1.5B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b3fd6ef3d5acd4ddeeeaf0e290f28d53a304e011eacc385fe846ad7a56b106b5
size 1016845376

3
Dolphin3.0-Qwen2.5-1.5B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b7d7227f3bc6134cfe05a9c707159d9446c1ec9c73fa45ca2e284617a34e81bb
size 1042571840

3
Dolphin3.0-Qwen2.5-1.5B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7caa630a60c8831a509e2663e1761355fa24bcf6ccc03e3cc767e5b5747a3be5
size 986051648

3
Dolphin3.0-Qwen2.5-1.5B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:95370435ab49f9fd04313d0aca6b0c4e0b269aa10e13ce7de14b42b49a0e6d9f
size 940315712

3
Dolphin3.0-Qwen2.5-1.5B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:41eda912c9528f2c254f1a77363c985a38418283db51ace4c0516d87bfaf8f29
size 1181573696

3
Dolphin3.0-Qwen2.5-1.5B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3cd2bb1a5cfbdb2ac496fedba4149148a73aeab6273ecbfd327989e64c601725
size 1125053504

3
Dolphin3.0-Qwen2.5-1.5B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4cae0808171dd1fe0523672ead8b4e87a55945ab79174798a713cf573e95e12d
size 1098732608

3
Dolphin3.0-Qwen2.5-1.5B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f5f2cc4d023e5958670c2ce1cf9e8f10b68e213d1a2c499044239c3978fc3349
size 1272742976

3
Dolphin3.0-Qwen2.5-1.5B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14ed7555f95ae45a441c0a4406a01edc1c604da3a7604b0b97e5e9cfbae347e3
size 1329263168

3
Dolphin3.0-Qwen2.5-1.5B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a6e0e6f801428a083b39a25897a08eee3ab8a0f091573299c53d8f85cc8b3e04
size 1646576192

3
Dolphin3.0-Qwen2.5-1.5B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c92a8d8e31f164c3eb40de7a98d5d1613a29614857dcef15d24cb419dd866ff
size 3093672512

3
Dolphin3.0-Qwen2.5-1.5B-f32.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:42a6e6f16b4d4efdeabf62a7ca43223f094030c590aab31c4ac475959d6b6357
size 6180811040

3
Dolphin3.0-Qwen2.5-1.5B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0332e734df00586df232b15970e713adabd5070c56694d62e2808e0b183f3a11
size 2042214

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-Qwen2.5-1.5B
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-Qwen2.5-1.5B
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-Qwen2.5-1.5B
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-Qwen2.5-1.5B-f32.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-f32.gguf) | f32 | 6.18GB | false | Full F32 weights. |
| [Dolphin3.0-Qwen2.5-1.5B-f16.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-f16.gguf) | f16 | 3.09GB | false | Full F16 weights. |
| [Dolphin3.0-Qwen2.5-1.5B-Q8_0.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q8_0.gguf) | Q8_0 | 1.65GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Dolphin3.0-Qwen2.5-1.5B-Q6_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q6_K_L.gguf) | Q6_K_L | 1.33GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q6_K.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q6_K.gguf) | Q6_K | 1.27GB | false | Very high quality, near perfect, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q5_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q5_K_L.gguf) | Q5_K_L | 1.18GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q5_K_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q5_K_M.gguf) | Q5_K_M | 1.13GB | false | High quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q5_K_S.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q5_K_S.gguf) | Q5_K_S | 1.10GB | false | High quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q4_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q4_K_L.gguf) | Q4_K_L | 1.04GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q4_1.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q4_1.gguf) | Q4_1 | 1.02GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [Dolphin3.0-Qwen2.5-1.5B-Q4_K_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q4_K_M.gguf) | Q4_K_M | 0.99GB | false | Good quality, default size for most use cases, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q4_K_S.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q4_K_S.gguf) | Q4_K_S | 0.94GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q4_0.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q4_0.gguf) | Q4_0 | 0.94GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [Dolphin3.0-Qwen2.5-1.5B-IQ4_NL.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-IQ4_NL.gguf) | IQ4_NL | 0.94GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [Dolphin3.0-Qwen2.5-1.5B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q3_K_XL.gguf) | Q3_K_XL | 0.94GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Dolphin3.0-Qwen2.5-1.5B-IQ4_XS.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-IQ4_XS.gguf) | IQ4_XS | 0.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Dolphin3.0-Qwen2.5-1.5B-Q3_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q3_K_L.gguf) | Q3_K_L | 0.88GB | false | Lower quality but usable, good for low RAM availability. |
| [Dolphin3.0-Qwen2.5-1.5B-Q3_K_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q3_K_M.gguf) | Q3_K_M | 0.82GB | false | Low quality. |
| [Dolphin3.0-Qwen2.5-1.5B-IQ3_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-IQ3_M.gguf) | IQ3_M | 0.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Dolphin3.0-Qwen2.5-1.5B-Q3_K_S.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q3_K_S.gguf) | Q3_K_S | 0.76GB | false | Low quality, not recommended. |
| [Dolphin3.0-Qwen2.5-1.5B-IQ3_XS.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-IQ3_XS.gguf) | IQ3_XS | 0.73GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Dolphin3.0-Qwen2.5-1.5B-Q2_K_L.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q2_K_L.gguf) | Q2_K_L | 0.73GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Dolphin3.0-Qwen2.5-1.5B-Q2_K.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-Q2_K.gguf) | Q2_K | 0.68GB | false | Very low quality but surprisingly usable. |
| [Dolphin3.0-Qwen2.5-1.5B-IQ2_M.gguf](https://huggingface.co/bartowski/Dolphin3.0-Qwen2.5-1.5B-GGUF/blob/main/Dolphin3.0-Qwen2.5-1.5B-IQ2_M.gguf) | IQ2_M | 0.60GB | 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-Qwen2.5-1.5B-GGUF --include "Dolphin3.0-Qwen2.5-1.5B-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-Qwen2.5-1.5B-GGUF --include "Dolphin3.0-Qwen2.5-1.5B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Dolphin3.0-Qwen2.5-1.5B-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}