初始化项目，由ModelHub XC社区提供模型
Model: bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF Source: Original Platform
This commit is contained in:
ModelHub XC
60
.gitattributes
vendored
Normal file
60
.gitattributes
vendored
Normal 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
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-bf16.gguf filter=lfs diff=lfs merge=lfs -text
|
||||
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404.imatrix filter=lfs diff=lfs merge=lfs -text
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ2_M.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ2_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab842ab43ee3acdf191f9d4054aa47bf30b13f5855f1fdda1039d8406b9494e9
|
||||
size 1229032256
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_M.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_M.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:180f874709ddf7baa282cf60e0a8e881c977fa7b0a469e8617e51f17ae2d2ad6
|
||||
size 1599669056
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f1165ad0b2b8dc22888d760251085800201dbd64a867c9fbf012b3c34caf9a0
|
||||
size 1476789056
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b7baf84cefe4f823bd44e00d3c5b9b1576917841b05f33b581df16125c958ac2
|
||||
size 1348766528
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d0148f1699819990e2ee76f465056ed0268590d41389eceb22cc317c9b3950c3
|
||||
size 1917190976
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5c817b5124d2b79ea2d37f1c19c3ec2a4e20170101788b3a21308a8615482658
|
||||
size 1829110592
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4b5bf0d8c23a37437eabf1f19d7be5df3c224657aca5abb3d887d29a8fa637c1
|
||||
size 1363936064
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b3cb763ed3054abc9f0d5aa9dfe738480bc587a085483c391a76e9d8b53cfbe7
|
||||
size 1459358528
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:68d6a33e1cd3de1a1e5a34c70414854c94f41302c6041b3f212e7c334457af4a
|
||||
size 1815348032
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0de618cd43522aadb4e870951800f01d5c28d4f2c6a811e53440c36a3fadf2c0
|
||||
size 1687159616
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5cdb6bb22273b568b98ecd917ade95baa112e3fe8956301a50f84510d53f8a3b
|
||||
size 1542849344
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8375e7f9398ce3e55f2fb8d9fc84274ac94b9f9f2ec2b8f7d1e68be2a10d52c2
|
||||
size 1910770496
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_0.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9d8958257d7d4c4349c9745207416833716c68efdd2b36d79477955be88a7dcd
|
||||
size 1921909568
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_1.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_1.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bd915c288951bdbcc9feaac2f6fea582fb3c094fa9907e89b8b6602bb538f2a8
|
||||
size 2093351744
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fef7e772b63d52a75815375fdf863fd6ab5387e705c9a7b50d30c790a2b2027c
|
||||
size 2114800448
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b9f01bead9e163db9351af036d8d63ef479d7d48a1bb44934ead732a180f371c
|
||||
size 2019377984
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1fd54a1acd9d62ac57f29e8c71eb4671d2163544f5d6e26d655e218707fbb2cf
|
||||
size 1928201024
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c5dab25a50226b3a162fc3d510464673b3b31a0f97c3efb54a51776146ca3e28
|
||||
size 2417576768
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:49bf548cbe88acf8fcf2fa91200fbd19a3dfe66c75a7d9b51d86f6b06b94ed3a
|
||||
size 2322154304
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d8e3b1122ec98f41d63b52ab0d8b3f0991baedb7bb92ee8e9c79dec03f22f6d7
|
||||
size 2269512512
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cc77440b0db36c5b420a6b5c8ae0a655f4751ac60e045937c20014c49349bed2
|
||||
size 2643854144
|
||||
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d8296373bcb44d4246408061bafd970a1420bbea35d8f310d253253647cb4f96
|
||||
size 2739276608
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q8_0.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q8_0.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:df2a8ceef09ea94a851a3c52e51e650dec50d32245334e1806276efbbef437ef
|
||||
size 3421899584
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-bf16.gguf
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-bf16.gguf
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fa587c5f1be5b76e97832c95ff3d692ec361e4fa8c5f83aa902c65e02ecb6add
|
||||
size 6433688064
|
||||
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404.imatrix
Normal file
3
Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404.imatrix
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:04e7a0c8c6cea663c011519ac69b39450d75da949d92c8e3e2e691d675017f79
|
||||
size 2988390
|
||||
177
README.md
Normal file
177
README.md
Normal file
@@ -0,0 +1,177 @@
|
||||
---
|
||||
quantized_by: bartowski
|
||||
pipeline_tag: text-generation
|
||||
metrics:
|
||||
- accuracy
|
||||
language:
|
||||
- en
|
||||
base_model: Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
|
||||
base_model_relation: quantized
|
||||
---
|
||||
|
||||
## Llamacpp imatrix Quantizations of ReZero-v0.1-llama-3.2-3b-it-grpo-250404 by Menlo
|
||||
|
||||
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b5132">b5132</a> for quantization.
|
||||
|
||||
Original model: https://huggingface.co/Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404
|
||||
|
||||
All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
|
||||
|
||||
Run them in [LM Studio](https://lmstudio.ai/)
|
||||
|
||||
Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project
|
||||
|
||||
## Prompt format
|
||||
|
||||
```
|
||||
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
|
||||
|
||||
Cutting Knowledge Date: December 2023
|
||||
Today Date: 16 Apr 2025
|
||||
|
||||
{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>
|
||||
|
||||
{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
```
|
||||
|
||||
## Download a file (not the whole branch) from below:
|
||||
|
||||
| Filename | Quant type | File Size | Split | Description |
|
||||
| -------- | ---------- | --------- | ----- | ----------- |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-bf16.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-bf16.gguf) | bf16 | 6.43GB | false | Full BF16 weights. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q8_0.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q8_0.gguf) | Q8_0 | 3.42GB | false | Extremely high quality, generally unneeded but max available quant. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K_L.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K_L.gguf) | Q6_K_L | 2.74GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q6_K.gguf) | Q6_K | 2.64GB | false | Very high quality, near perfect, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_L.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_L.gguf) | Q5_K_L | 2.42GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_M.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_M.gguf) | Q5_K_M | 2.32GB | false | High quality, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_S.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q5_K_S.gguf) | Q5_K_S | 2.27GB | false | High quality, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_L.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_L.gguf) | Q4_K_L | 2.11GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_1.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_1.gguf) | Q4_1 | 2.09GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf) | Q4_K_M | 2.02GB | false | Good quality, default size for most use cases, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_S.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_S.gguf) | Q4_K_S | 1.93GB | false | Slightly lower quality with more space savings, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_0.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_0.gguf) | Q4_0 | 1.92GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ4_NL.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ4_NL.gguf) | IQ4_NL | 1.92GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_XL.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_XL.gguf) | Q3_K_XL | 1.91GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ4_XS.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ4_XS.gguf) | IQ4_XS | 1.83GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_L.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_L.gguf) | Q3_K_L | 1.82GB | false | Lower quality but usable, good for low RAM availability. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_M.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_M.gguf) | Q3_K_M | 1.69GB | false | Low quality. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_M.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_M.gguf) | IQ3_M | 1.60GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_S.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q3_K_S.gguf) | Q3_K_S | 1.54GB | false | Low quality, not recommended. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_XS.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_XS.gguf) | IQ3_XS | 1.48GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K_L.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K_L.gguf) | Q2_K_L | 1.46GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q2_K.gguf) | Q2_K | 1.36GB | false | Very low quality but surprisingly usable. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_XXS.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ3_XXS.gguf) | IQ3_XXS | 1.35GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
|
||||
| [ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ2_M.gguf](https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/blob/main/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-IQ2_M.gguf) | IQ2_M | 1.23GB | 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/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF --include "Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-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/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF --include "Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q8_0/*" --local-dir ./
|
||||
```
|
||||
|
||||
You can either specify a new local-dir (Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-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, 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
|
||||
Reference in New Issue
Block a user