bartowski/Llama-3.1-8B-Stheno-v3.4-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/Llama-3.1-8B-Stheno-v3.4-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-18 13:49:06 +08:00
commit 5d35285283
28 changed files with 268 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
Llama-3.1-8B-Stheno-v3.4-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4-f16.gguf filter=lfs diff=lfs merge=lfs -text
Llama-3.1-8B-Stheno-v3.4.imatrix filter=lfs diff=lfs merge=lfs -text

3
Llama-3.1-8B-Stheno-v3.4-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:25e8b6d03e2bca50c9a52062b37f3e42b6af97aaa94db4b18e4ce6db78cd1243
size 2948281856

3
Llama-3.1-8B-Stheno-v3.4-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca72ac54cecb7f5bca9dbba78a6e3238a5dcd614059f497fc3f2add6dd1b2d77
size 3784824320

3
Llama-3.1-8B-Stheno-v3.4-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c5b0bce076d5383b522b505b57125965268fe471a96ce1c0eacfb2d10e7151d
size 3518748160

3
Llama-3.1-8B-Stheno-v3.4-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7a96b132afd2a975d4ae5ff40a17a88ea3b72e34e7222d34200492b9f711ee7d
size 4447663616

3
Llama-3.1-8B-Stheno-v3.4-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:261a161cf89588d6d8890ca51841b9cdaf83baf315a78b36849a6265ddeec210
size 3179132416

3
Llama-3.1-8B-Stheno-v3.4-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9679e309dd359cb092904fbce160ea73c8e037ea35c021995307d80ac41b1e3f
size 3692156416

3
Llama-3.1-8B-Stheno-v3.4-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:89a42d33cb123be3103695ad969fe14a9ca3a80bb8b1805e950e2ad18d96a9af
size 4321957376

3
Llama-3.1-8B-Stheno-v3.4-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b9006b3b9437d31764382b8c4a544cdafa191f1eccec4b61a352853ee2f3b4ef
size 4018918912

3
Llama-3.1-8B-Stheno-v3.4-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a3bbe80a6612c932834c497ea146b7866f702d5cdd1bfb171698b0c0d1f8e9a
size 3664500224

3
Llama-3.1-8B-Stheno-v3.4-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:585e7fab4688e991ab60b0b37b259343e2b54005cae6bb6e3dfffd80c77bc729
size 4781626880

3
Llama-3.1-8B-Stheno-v3.4-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:052b13d64cd809b1d2e4b6ff9c5b6be05a6a7aea770c2cbd0965964ae2dafaa8
size 4675892736

3
Llama-3.1-8B-Stheno-v3.4-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c5c052bfb998ce54492ecbd21a1d9452287bcc478fe1e53b369c04b85d471bcd
size 4661212672

3
Llama-3.1-8B-Stheno-v3.4-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47487cbe39f19b6f6aabe16f20485f5f869c9456e83db139f3d72b4fbb812397
size 4661212672

3
Llama-3.1-8B-Stheno-v3.4-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5a407c0d0d0ecf65c283ff9d56ce48a927c07f927e30aec7cc20a39372f3a0f8
size 4661212672

3
Llama-3.1-8B-Stheno-v3.4-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d6d4039a7e3f4e779e6d809ef31c10fb85268f34e12d763791bb596098e3af1
size 5310633472

3
Llama-3.1-8B-Stheno-v3.4-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ca635b6dad84f3d093ab5cf93d88e809d8d5e6e7e1729cf94e597e46e69d6793
size 4920735232

3
Llama-3.1-8B-Stheno-v3.4-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e0a8f4d498fff80ebd2447b15d5797afc97a51f2791bc164efc1b7716584e77c
size 4692669952

3
Llama-3.1-8B-Stheno-v3.4-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c6158c9854551b7a43048c762155133796fe74f2a0dfbf8eec1a015ba23677a4
size 6057219584

3
Llama-3.1-8B-Stheno-v3.4-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:911ea8cd440acb246616bf1809ba5d944a94b458af9055ae59e119ef5c55eba0
size 5732988416

3
Llama-3.1-8B-Stheno-v3.4-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6237da63768e19a2dee825ca7741e27708452e01ee58aa64d213c4a4942dadeb
size 5599294976

3
Llama-3.1-8B-Stheno-v3.4-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b92db556960b42065238a0c71e2553e6ca9179a60bfd38ac32be063b7d95e9bd
size 6596007424

3
Llama-3.1-8B-Stheno-v3.4-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3e4a924bad57d53a86d57434fb1308f32e1734c09a6abec835d49d3d6e055e05
size 6850467328

3
Llama-3.1-8B-Stheno-v3.4-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d066cd9848bf6d450119f1f56bfb9bcae51d576ed489f013af43f8f47b17ac0
size 8540771840

3
Llama-3.1-8B-Stheno-v3.4-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:407a74c4b2f45a7673af6118ab60868514ac8664641468f42417cd64416b2959
size 16068891872

3
Llama-3.1-8B-Stheno-v3.4.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:899d1769668556d56dce457b8db3e098cc54b04d0290e72fe348a1be5803a3e0
size 4988170

132
README.md Normal file
View File

@@ -0,0 +1,132 @@
---
base_model: Sao10K/Llama-3.1-8B-Stheno-v3.4
datasets:
- Setiaku/Stheno-v3.4-Instruct
- Setiaku/Stheno-3.4-Creative-2
language:
- en
license: cc-by-nc-4.0
pipeline_tag: text-generation
quantized_by: bartowski
---
## Llamacpp imatrix Quantizations of Llama-3.1-8B-Stheno-v3.4
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3825">b3825</a> for quantization.
Original model: https://huggingface.co/Sao10K/Llama-3.1-8B-Stheno-v3.4
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
```
<|begin_of_text|><|start_header_id|>system<|end_header_id|>
{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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [Llama-3.1-8B-Stheno-v3.4-f16.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [Llama-3.1-8B-Stheno-v3.4-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Llama-3.1-8B-Stheno-v3.4-Q6_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q5_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q5_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for must use cases, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q3_K_XL.gguf) | Q3_K_XL | 4.78GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [Llama-3.1-8B-Stheno-v3.4-Q4_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q4_0.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Llama-3.1-8B-Stheno-v3.4-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.66GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). |
| [Llama-3.1-8B-Stheno-v3.4-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.66GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). |
| [Llama-3.1-8B-Stheno-v3.4-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q4_0_4_4.gguf) | Q4_0_4_4 | 4.66GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. |
| [Llama-3.1-8B-Stheno-v3.4-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Llama-3.1-8B-Stheno-v3.4-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [Llama-3.1-8B-Stheno-v3.4-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [Llama-3.1-8B-Stheno-v3.4-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Llama-3.1-8B-Stheno-v3.4-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Llama-3.1-8B-Stheno-v3.4-Q3_K_S.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [Llama-3.1-8B-Stheno-v3.4-IQ3_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Llama-3.1-8B-Stheno-v3.4-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [Llama-3.1-8B-Stheno-v3.4-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3.1-8B-Stheno-v3.4-GGUF/blob/main/Llama-3.1-8B-Stheno-v3.4-IQ2_M.gguf) | IQ2_M | 2.95GB | 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.
Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
Thanks!
## Downloading using huggingface-cli
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/Llama-3.1-8B-Stheno-v3.4-GGUF --include "Llama-3.1-8B-Stheno-v3.4-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/Llama-3.1-8B-Stheno-v3.4-GGUF --include "Llama-3.1-8B-Stheno-v3.4-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Llama-3.1-8B-Stheno-v3.4-Q8_0) or download them all in place (./)
## Q4_0_X_X
These are *NOT* for Metal (Apple) offloading, only ARM chips.
If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
## Which file should I choose?
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.
## 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}