初始化项目，由ModelHub XC社区提供模型
Model: bartowski/NousResearch_NousCoder-14B-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
75
.gitattributes
vendored
Normal file
75
.gitattributes
vendored
Normal file
@@ -0,0 +1,75 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 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
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* 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
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
NousResearch_NousCoder-14B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
NousResearch_NousCoder-14B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
3
NousResearch_NousCoder-14B-IQ2_M.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fac58255ebd66d1a9034dd023bcb6f177b112be2469700f47139672a9b91ccbb
|
||||
size 5322942592
|
||||
3
NousResearch_NousCoder-14B-IQ2_S.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ2_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:542d1d5279ecb964ab9f8b9eac270a15329f1258475b011eb0ef2b456b54b851
|
||||
size 4963313792
|
||||
3
NousResearch_NousCoder-14B-IQ2_XS.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ2_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:74e1a5103a6e1a6d0faf73f276710d2547483f4f2f3901462cd820b14783137c
|
||||
size 4691590272
|
||||
3
NousResearch_NousCoder-14B-IQ3_M.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7539f0aa27d7301315ff4f6a5ef450047e8506718e73dcf2fce7ce32e6ee124d
|
||||
size 6883411072
|
||||
3
NousResearch_NousCoder-14B-IQ3_XS.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ3_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3ba98c3f191f3c9e5000197fd980635ca5cbb034d8ca5b6b7cf0d68cd3f2eac3
|
||||
size 6375302272
|
||||
3
NousResearch_NousCoder-14B-IQ3_XXS.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ3_XXS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ad65e5d05dc32423c27738a66367f6482123d081cef94253fe6f3ca52bbaaa01
|
||||
size 5942667392
|
||||
3
NousResearch_NousCoder-14B-IQ4_NL.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ4_NL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7302cf5d7bf6efc992c341059e89404bed1dd58f136fda2a2caae3eb19c7c8ed
|
||||
size 8541364352
|
||||
3
NousResearch_NousCoder-14B-IQ4_XS.gguf
Normal file
3
NousResearch_NousCoder-14B-IQ4_XS.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:711fd9643ae0c55200dece0b080eb0c2874293c2a1b47b027ff320b6b8cdd513
|
||||
size 8110731392
|
||||
3
NousResearch_NousCoder-14B-Q2_K.gguf
Normal file
3
NousResearch_NousCoder-14B-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5077b1cbf30b241544c9d57ad115a9813398298cc1694a8daca0b9c49f50ffbd
|
||||
size 5753985152
|
||||
3
NousResearch_NousCoder-14B-Q2_K_L.gguf
Normal file
3
NousResearch_NousCoder-14B-Q2_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ccfb362e53ef51e5ae18101e67471e721ce2b49a41187a81590210c53561b471
|
||||
size 6513665152
|
||||
3
NousResearch_NousCoder-14B-Q3_K_L.gguf
Normal file
3
NousResearch_NousCoder-14B-Q3_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c1569321bceac5b124576d054bdc9a5a60b7d1865e0a8dc77c5c213969f52c74
|
||||
size 7900652672
|
||||
3
NousResearch_NousCoder-14B-Q3_K_M.gguf
Normal file
3
NousResearch_NousCoder-14B-Q3_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7006151c7b9370f0a5ee3b0816ab725e3906db7cc8f558bee340c5a256fe9404
|
||||
size 7321314432
|
||||
3
NousResearch_NousCoder-14B-Q3_K_S.gguf
Normal file
3
NousResearch_NousCoder-14B-Q3_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ccbcc46f6937167000e852eeaa00cc3a16aa456f99804b882f09d00f6df1af1c
|
||||
size 6657107072
|
||||
3
NousResearch_NousCoder-14B-Q3_K_XL.gguf
Normal file
3
NousResearch_NousCoder-14B-Q3_K_XL.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7c9c77e7cb6f280d9be3e5a37f28affb8695b349990baaf13722c882e312216c
|
||||
size 8581325952
|
||||
3
NousResearch_NousCoder-14B-Q4_0.gguf
Normal file
3
NousResearch_NousCoder-14B-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:230b521540e3faa9889aae0940acc65da50fd81041b56b342a3e5beabd02d041
|
||||
size 8543002752
|
||||
3
NousResearch_NousCoder-14B-Q4_1.gguf
Normal file
3
NousResearch_NousCoder-14B-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a9af81cf064044b6571fc58745bccd766291994be7845808de622c197d86a4b4
|
||||
size 9389523072
|
||||
3
NousResearch_NousCoder-14B-Q4_K_L.gguf
Normal file
3
NousResearch_NousCoder-14B-Q4_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd44f8b8631f321ea0e04236f87b4639a4077cad9800dbe8eac650b2ba726cfb
|
||||
size 9579111552
|
||||
3
NousResearch_NousCoder-14B-Q4_K_M.gguf
Normal file
3
NousResearch_NousCoder-14B-Q4_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9cc51afc755319db42a6324baf3395436cce5954dc87df95d3b9e7d625610624
|
||||
size 9001754752
|
||||
3
NousResearch_NousCoder-14B-Q4_K_S.gguf
Normal file
3
NousResearch_NousCoder-14B-Q4_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9b44816ca53363e0be52e90841ac59b67eb0ccbc47fd483f2dfb21a7206a7179
|
||||
size 8573476992
|
||||
3
NousResearch_NousCoder-14B-Q5_K_L.gguf
Normal file
3
NousResearch_NousCoder-14B-Q5_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f930cc92d627ba45bf248e1357a86d5519b490d87fabf48e50e48b42660b8177
|
||||
size 10994689152
|
||||
3
NousResearch_NousCoder-14B-Q5_K_M.gguf
Normal file
3
NousResearch_NousCoder-14B-Q5_K_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3954093ee088e731f480bca348e72d403b1b0e9de7ab52e2fc7a1cf5e9768244
|
||||
size 10514571392
|
||||
3
NousResearch_NousCoder-14B-Q5_K_S.gguf
Normal file
3
NousResearch_NousCoder-14B-Q5_K_S.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ef7a41c84b3ce0b62f1653969d9242d222d9e04d1fca1a3a7b6885cb5bc448be
|
||||
size 10263896192
|
||||
3
NousResearch_NousCoder-14B-Q6_K.gguf
Normal file
3
NousResearch_NousCoder-14B-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:919959ba34f0a6fbda21de9268a04aea487d3a0301854ac4c8c4169641fd7446
|
||||
size 12121939072
|
||||
3
NousResearch_NousCoder-14B-Q6_K_L.gguf
Normal file
3
NousResearch_NousCoder-14B-Q6_K_L.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:65492cc9ede76255f1ea2748c04ec98a274b7b2778be2ddf2af674498fa9135b
|
||||
size 12498740352
|
||||
3
NousResearch_NousCoder-14B-Q8_0.gguf
Normal file
3
NousResearch_NousCoder-14B-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:93ddc46421be122e98d18c4603a89020d98e8f45de8a04a4e038d11ea536f55b
|
||||
size 15698535552
|
||||
3
NousResearch_NousCoder-14B-bf16.gguf
Normal file
3
NousResearch_NousCoder-14B-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d2a758dc70dec553da18ecb7fd5c7171dbdabac0d72c0316c5c3e4d3a74f995f
|
||||
size 29543424864
|
||||
3
NousResearch_NousCoder-14B-imatrix.gguf
Normal file
3
NousResearch_NousCoder-14B-imatrix.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bc083fa2efae828e14686ff137b7077537504b1584ed5d5ad6aca4d49c05c654
|
||||
size 7743584
|
||||
185
README.md
Normal file
185
README.md
Normal file
@@ -0,0 +1,185 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: text-generation
|
||||
base_model_relation: quantized
|
||||
datasets:
|
||||
- livecodebench/code_generation_lite
|
||||
- agentica-org/DeepCoder-Preview-Dataset
|
||||
- NousResearch/lcb_test
|
||||
- NousResearch/RLVR_Coding_Problems
|
||||
base_model: NousResearch/NousCoder-14B
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of NousCoder-14B by NousResearch
|
||||
|
||||
Using <a href="https://github.com/ggml-org/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggml-org/llama.cpp/releases/tag/b7652">b7652</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/NousResearch/NousCoder-14B
|
||||
|
||||
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/82ae9b520227f57d79ba04add13d0d0d)
|
||||
|
||||
Run them in your choice of tools:
|
||||
|
||||
- [llama.cpp](https://github.com/ggml-org/llama.cpp)
|
||||
- [LM Studio](https://lmstudio.ai/)
|
||||
- [koboldcpp](https://github.com/LostRuins/koboldcpp)
|
||||
- [Jan AI](https://www.jan.ai/)
|
||||
- [Text Generation Web UI](https://github.com/oobabooga/text-generation-webui)
|
||||
- [LoLLMs](https://github.com/ParisNeo/lollms)
|
||||
|
||||
Note: if it's a newly supported model, you may need to wait for an update from the developers.
|
||||
|
||||
## 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 |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [NousCoder-14B-bf16.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-bf16.gguf) | bf16 | 29.54GB | false | Full BF16 weights. |
|
||||
| [NousCoder-14B-Q8_0.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q8_0.gguf) | Q8_0 | 15.70GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [NousCoder-14B-Q6_K_L.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q6_K_L.gguf) | Q6_K_L | 12.50GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [NousCoder-14B-Q6_K.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q6_K.gguf) | Q6_K | 12.12GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [NousCoder-14B-Q5_K_L.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q5_K_L.gguf) | Q5_K_L | 10.99GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [NousCoder-14B-Q5_K_M.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q5_K_M.gguf) | Q5_K_M | 10.51GB | false | High quality, *recommended*. |
|
||||
| [NousCoder-14B-Q5_K_S.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q5_K_S.gguf) | Q5_K_S | 10.26GB | false | High quality, *recommended*. |
|
||||
| [NousCoder-14B-Q4_K_L.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q4_K_L.gguf) | Q4_K_L | 9.58GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [NousCoder-14B-Q4_1.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q4_1.gguf) | Q4_1 | 9.39GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [NousCoder-14B-Q4_K_M.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q4_K_M.gguf) | Q4_K_M | 9.00GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [NousCoder-14B-Q3_K_XL.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q3_K_XL.gguf) | Q3_K_XL | 8.58GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||
| [NousCoder-14B-Q4_K_S.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q4_K_S.gguf) | Q4_K_S | 8.57GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [NousCoder-14B-Q4_0.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q4_0.gguf) | Q4_0 | 8.54GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [NousCoder-14B-IQ4_NL.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ4_NL.gguf) | IQ4_NL | 8.54GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [NousCoder-14B-IQ4_XS.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ4_XS.gguf) | IQ4_XS | 8.11GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [NousCoder-14B-Q3_K_L.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q3_K_L.gguf) | Q3_K_L | 7.90GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
| [NousCoder-14B-Q3_K_M.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q3_K_M.gguf) | Q3_K_M | 7.32GB | false | Low quality. |
|
||||
| [NousCoder-14B-IQ3_M.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ3_M.gguf) | IQ3_M | 6.88GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [NousCoder-14B-Q3_K_S.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q3_K_S.gguf) | Q3_K_S | 6.66GB | false | Low quality, not recommended. |
|
||||
| [NousCoder-14B-Q2_K_L.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q2_K_L.gguf) | Q2_K_L | 6.51GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [NousCoder-14B-IQ3_XS.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ3_XS.gguf) | IQ3_XS | 6.38GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [NousCoder-14B-IQ3_XXS.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ3_XXS.gguf) | IQ3_XXS | 5.94GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [NousCoder-14B-Q2_K.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-Q2_K.gguf) | Q2_K | 5.75GB | false | Very low quality but surprisingly usable. |
|
||||
| [NousCoder-14B-IQ2_M.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ2_M.gguf) | IQ2_M | 5.32GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
|
||||
| [NousCoder-14B-IQ2_S.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ2_S.gguf) | IQ2_S | 4.96GB | false | Low quality, uses SOTA techniques to be usable. |
|
||||
| [NousCoder-14B-IQ2_XS.gguf](https://huggingface.co/bartowski/NousResearch_NousCoder-14B-GGUF/blob/main/NousResearch_NousCoder-14B-IQ2_XS.gguf) | IQ2_XS | 4.69GB | false | Low quality, uses SOTA techniques to be 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/NousResearch_NousCoder-14B-GGUF --include "NousResearch_NousCoder-14B-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/NousResearch_NousCoder-14B-GGUF --include "NousResearch_NousCoder-14B-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (NousResearch_NousCoder-14B-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/ggml-org/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/ggml-org/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/ggml-org/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/ggml-org/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, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
|
||||
|
||||
</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.
|
||||
|
||||
Thank you to LM Studio for sponsoring my work.
|
||||
|
||||
Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
Reference in New Issue
Block a user