bartowski/Open-Insurance-LLM-Llama3-8B-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/Open-Insurance-LLM-Llama3-8B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-18 04:26:12 +08:00
commit c7479bcd6e
28 changed files with 327 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
Open-Insurance-LLM-Llama3-8B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B-f16.gguf filter=lfs diff=lfs merge=lfs -text
Open-Insurance-LLM-Llama3-8B.imatrix filter=lfs diff=lfs merge=lfs -text

3
Open-Insurance-LLM-Llama3-8B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1ed315f7d7778b51929fe1aa915f9421dad0c89013acbf8de2b90a7551e6d8a
size 2948282336

3
Open-Insurance-LLM-Llama3-8B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18907b8cdea3c1671c0d38cea94d8c3e8c6bd95da6709b67754d183d2c71ee26
size 3784824800

3
Open-Insurance-LLM-Llama3-8B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:21101ee47080a56f6e2b08a843fe62ff6f55edf8f4eca09d491a92dbd98280d8
size 3518748640

3
Open-Insurance-LLM-Llama3-8B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0439ac778d86f9b4e0b62e16a289cf3638f919425cee2b7e9e43008af38c04c0
size 4447664096

3
Open-Insurance-LLM-Llama3-8B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9108b845bea66fd5aba15c397c007b4cc5f342d1d28b3a6d86e0af604ae0c884
size 3179132896

3
Open-Insurance-LLM-Llama3-8B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0e5c82e494280e7ce52e345966ecf4f48400a65a98de0d9804512dab4f2142c8
size 3692156896

3
Open-Insurance-LLM-Llama3-8B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4356c9fe6f4e0150e5a40e97f38cdaeb84fcdeb3d99abe61066b4c53142ebf30
size 4321957856

3
Open-Insurance-LLM-Llama3-8B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d910cb7a180d77d620117f6dd0c3f20f4940feee656a0a39a2f3064800102074
size 4018919392

3
Open-Insurance-LLM-Llama3-8B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2224a828a13b6e8cce60a7e4cd98741c17db3b87e547ca2676318e825ac09c89
size 3664500704

3
Open-Insurance-LLM-Llama3-8B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4ce51a9b3ec78d130033dc310571be82e63bdf2cabd49622b9bbcd4a90ad3278
size 4781627360

3
Open-Insurance-LLM-Llama3-8B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a669c0ab87260fd11115dd3289ca28ed18730863e78b37ee5ddc77a478e27410
size 4675893216

3
Open-Insurance-LLM-Llama3-8B-Q4_0_4_4.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8fc4509b611c962cc0a971f4ada08085de8001b7f53139c671de16738ee0eeb8
size 4661213152

3
Open-Insurance-LLM-Llama3-8B-Q4_0_4_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c23198aceafe4de5dc02cd2e16556b44e88df6e96f11b409ab05f3ed830bb305
size 4661213152

3
Open-Insurance-LLM-Llama3-8B-Q4_0_8_8.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ebc1dddd7e1df25a38af6b2d6321c030565bde8b156a147846747c8584d7620d
size 4661213152

3
Open-Insurance-LLM-Llama3-8B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:89e10cd3f878a74d3ac5b836854a74f7f181cb5e8d75084130ce25908d4cbbbc
size 5310633952

3
Open-Insurance-LLM-Llama3-8B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ddd04792869b09ba833f1eb9fc0169be1a697153df087af86bbaa7054cfbc04f
size 4920735712

3
Open-Insurance-LLM-Llama3-8B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e0582e572649745604b13bbcfcc6b36386eef20ba34433180ec8e8caf11005e2
size 4692670432

3
Open-Insurance-LLM-Llama3-8B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a77e6dd9f0e12b952e7884cf2989ab439bb3b03b45e9850bfee595aa00fefd7d
size 6057220064

3
Open-Insurance-LLM-Llama3-8B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:797a59f20ffbf9f5c7ab5397c773c4b535b8ed2cf3ef3836de12778491d46c88
size 5732988896

3
Open-Insurance-LLM-Llama3-8B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ceab613fb7bb23ee7b09e37635ec3924fbfca0463f61113e1c2491974d7869fc
size 5599295456

3
Open-Insurance-LLM-Llama3-8B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:229e480b368b115503123ae97ebb765371b63bec4e41bb6e97c6b7729d766f7c
size 6596007904

3
Open-Insurance-LLM-Llama3-8B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12e4ba554d35e306d83bcb7bde0fe90d98301404b4a5a5d2bbd8bdd9b9680235
size 6850467808

3
Open-Insurance-LLM-Llama3-8B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e62484cfde4916d1ede6588e0a889006232b96f003c5253cecc6f32e17502a60
size 8540772320

3
Open-Insurance-LLM-Llama3-8B-f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4c15f054e919d1e90fa47771941d59ceab708cc2793ab184ff2d202c0b09083a
size 16068892320

3
Open-Insurance-LLM-Llama3-8B.imatrix Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0a4b08e86fcb2e865c164d8c95ffd7aab71fe2d21130d97de0107b4ddefcb600
size 4988170

191
README.md Normal file
View File

@@ -0,0 +1,191 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
datasets:
- InsuranceQA
base_model: Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B
finetuned: Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B
tags:
- Text Generation
- Transformers
- llama
- llama-3
- 8B
- nvidia
- facebook
- meta
- LLM
- insurance
- research
- instruct
- chatqa-1.5
- chatqa
- finetune
- gpt4
- conversational
- text-generation-inference
license: llama3
quantized: Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B-GGUF
language:
- en
---
## Llamacpp imatrix Quantizations of Open-Insurance-LLM-Llama3-8B
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4132">b4132</a> for quantization.
Original model: https://huggingface.co/Raj-Maharajwala/Open-Insurance-LLM-Llama3-8B
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|>System: This is a chat between a user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions based on the context. The assistant should also indicate when the answer cannot be found in the context.
User: {prompt}
Assistant:
```
## Download a file (not the whole branch) from below:
| Filename | Quant type | File Size | Split | Description |
| -------- | ---------- | --------- | ----- | ----------- |
| [Open-Insurance-LLM-Llama3-8B-f16.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-f16.gguf) | f16 | 16.07GB | false | Full F16 weights. |
| [Open-Insurance-LLM-Llama3-8B-Q8_0.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q8_0.gguf) | Q8_0 | 8.54GB | false | Extremely high quality, generally unneeded but max available quant. |
| [Open-Insurance-LLM-Llama3-8B-Q6_K_L.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q6_K_L.gguf) | Q6_K_L | 6.85GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q6_K.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q6_K.gguf) | Q6_K | 6.60GB | false | Very high quality, near perfect, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q5_K_L.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q5_K_L.gguf) | Q5_K_L | 6.06GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q5_K_M.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q5_K_M.gguf) | Q5_K_M | 5.73GB | false | High quality, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q5_K_S.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q5_K_S.gguf) | Q5_K_S | 5.60GB | false | High quality, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q4_K_L.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q4_K_L.gguf) | Q4_K_L | 5.31GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q4_K_M.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q4_K_M.gguf) | Q4_K_M | 4.92GB | false | Good quality, default size for most use cases, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q3_K_XL.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-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. |
| [Open-Insurance-LLM-Llama3-8B-Q4_K_S.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q4_K_S.gguf) | Q4_K_S | 4.69GB | false | Slightly lower quality with more space savings, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q4_0.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q4_0.gguf) | Q4_0 | 4.68GB | false | Legacy format, generally not worth using over similarly sized formats |
| [Open-Insurance-LLM-Llama3-8B-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q4_0_8_8.gguf) | Q4_0_8_8 | 4.66GB | false | Optimized for ARM and AVX inference. Requires 'sve' support for ARM (see details below). *Don't use on Mac*. |
| [Open-Insurance-LLM-Llama3-8B-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q4_0_4_8.gguf) | Q4_0_4_8 | 4.66GB | false | Optimized for ARM inference. Requires 'i8mm' support (see details below). *Don't use on Mac*. |
| [Open-Insurance-LLM-Llama3-8B-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q4_0_4_4.gguf) | Q4_0_4_4 | 4.66GB | false | Optimized for ARM inference. Should work well on all ARM chips, not for use with GPUs. *Don't use on Mac*. |
| [Open-Insurance-LLM-Llama3-8B-IQ4_XS.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-IQ4_XS.gguf) | IQ4_XS | 4.45GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [Open-Insurance-LLM-Llama3-8B-Q3_K_L.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q3_K_L.gguf) | Q3_K_L | 4.32GB | false | Lower quality but usable, good for low RAM availability. |
| [Open-Insurance-LLM-Llama3-8B-Q3_K_M.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q3_K_M.gguf) | Q3_K_M | 4.02GB | false | Low quality. |
| [Open-Insurance-LLM-Llama3-8B-IQ3_M.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-IQ3_M.gguf) | IQ3_M | 3.78GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [Open-Insurance-LLM-Llama3-8B-Q2_K_L.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q2_K_L.gguf) | Q2_K_L | 3.69GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [Open-Insurance-LLM-Llama3-8B-Q3_K_S.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q3_K_S.gguf) | Q3_K_S | 3.66GB | false | Low quality, not recommended. |
| [Open-Insurance-LLM-Llama3-8B-IQ3_XS.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-IQ3_XS.gguf) | IQ3_XS | 3.52GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [Open-Insurance-LLM-Llama3-8B-Q2_K.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-Q2_K.gguf) | Q2_K | 3.18GB | false | Very low quality but surprisingly usable. |
| [Open-Insurance-LLM-Llama3-8B-IQ2_M.gguf](https://huggingface.co/bartowski/Open-Insurance-LLM-Llama3-8B-GGUF/blob/main/Open-Insurance-LLM-Llama3-8B-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.
## 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/Open-Insurance-LLM-Llama3-8B-GGUF --include "Open-Insurance-LLM-Llama3-8B-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/Open-Insurance-LLM-Llama3-8B-GGUF --include "Open-Insurance-LLM-Llama3-8B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (Open-Insurance-LLM-Llama3-8B-Q8_0) or download them all in place (./)
</details>
## Q4_0_X_X information
<details>
<summary>Click to view Q4_0_X_X information</summary>
These are *NOT* for Metal (Apple) or GPU (nvidia/AMD/intel) offloading, only ARM chips (and certain AVX2/AVX512 CPUs).
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!).
If you're using a CPU that supports AVX2 or AVX512 (typically server CPUs and AMD's latest Zen5 CPUs) and are not offloading to a GPU, the Q4_0_8_8 may offer a nice speed as well:
<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}