bartowski/ai21labs_AI21-Jamba2-3B-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/ai21labs_AI21-Jamba2-3B-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-04 09:16:12 +08:00
commit bdd2bcafb8
28 changed files with 327 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

73
.gitattributes vendored Normal file
View File

@@ -0,0 +1,73 @@
*.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
ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-bf16.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-imatrix.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text

178
README.md Normal file
View File

@@ -0,0 +1,178 @@
---
quantized_by: bartowski
pipeline_tag: text-generation
base_model_relation: quantized
base_model: ai21labs/AI21-Jamba2-3B
license: apache-2.0
---
## Llamacpp imatrix Quantizations of AI21-Jamba2-3B by ai21labs
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/ai21labs/AI21-Jamba2-3B
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
```
<|startoftext|><|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 |
| -------- | ---------- | --------- | ----- | ----------- |
| [AI21-Jamba2-3B-bf16.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-bf16.gguf) | bf16 | 6.40GB | false | Full BF16 weights. |
| [AI21-Jamba2-3B-Q8_0.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q8_0.gguf) | Q8_0 | 3.41GB | false | Extremely high quality, generally unneeded but max available quant. |
| [AI21-Jamba2-3B-Q6_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf) | Q6_K_L | 2.72GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
| [AI21-Jamba2-3B-Q6_K.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q6_K.gguf) | Q6_K | 2.64GB | false | Very high quality, near perfect, *recommended*. |
| [AI21-Jamba2-3B-Q5_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf) | Q5_K_L | 2.38GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
| [AI21-Jamba2-3B-Q5_K_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf) | Q5_K_M | 2.27GB | false | High quality, *recommended*. |
| [AI21-Jamba2-3B-Q5_K_S.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf) | Q5_K_S | 2.23GB | false | High quality, *recommended*. |
| [AI21-Jamba2-3B-Q4_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf) | Q4_K_L | 2.06GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
| [AI21-Jamba2-3B-Q4_1.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_1.gguf) | Q4_1 | 2.04GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. |
| [AI21-Jamba2-3B-Q4_K_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf) | Q4_K_M | 1.93GB | false | Good quality, default size for most use cases, *recommended*. |
| [AI21-Jamba2-3B-Q4_K_S.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf) | Q4_K_S | 1.86GB | false | Slightly lower quality with more space savings, *recommended*. |
| [AI21-Jamba2-3B-Q4_0.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q4_0.gguf) | Q4_0 | 1.86GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. |
| [AI21-Jamba2-3B-IQ4_NL.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf) | IQ4_NL | 1.85GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. |
| [AI21-Jamba2-3B-IQ4_XS.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf) | IQ4_XS | 1.76GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
| [AI21-Jamba2-3B-Q3_K_XL.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf) | Q3_K_XL | 1.76GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
| [AI21-Jamba2-3B-Q3_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf) | Q3_K_L | 1.61GB | false | Lower quality but usable, good for low RAM availability. |
| [AI21-Jamba2-3B-Q3_K_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf) | Q3_K_M | 1.54GB | false | Low quality. |
| [AI21-Jamba2-3B-IQ3_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ3_M.gguf) | IQ3_M | 1.47GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
| [AI21-Jamba2-3B-Q3_K_S.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf) | Q3_K_S | 1.46GB | false | Low quality, not recommended. |
| [AI21-Jamba2-3B-IQ3_XS.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf) | IQ3_XS | 1.41GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
| [AI21-Jamba2-3B-Q2_K_L.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf) | Q2_K_L | 1.37GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
| [AI21-Jamba2-3B-IQ3_XXS.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf) | IQ3_XXS | 1.30GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
| [AI21-Jamba2-3B-Q2_K.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-Q2_K.gguf) | Q2_K | 1.21GB | false | Very low quality but surprisingly usable. |
| [AI21-Jamba2-3B-IQ2_M.gguf](https://huggingface.co/bartowski/ai21labs_AI21-Jamba2-3B-GGUF/blob/main/ai21labs_AI21-Jamba2-3B-IQ2_M.gguf) | IQ2_M | 1.13GB | 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/ai21labs_AI21-Jamba2-3B-GGUF --include "ai21labs_AI21-Jamba2-3B-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/ai21labs_AI21-Jamba2-3B-GGUF --include "ai21labs_AI21-Jamba2-3B-Q8_0/*" --local-dir ./
```
You can either specify a new local-dir (ai21labs_AI21-Jamba2-3B-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

3
ai21labs_AI21-Jamba2-3B-IQ2_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f1aec91f4f91bdb800ef84727d18a7b8b528cbca321c66c6acdccc06dff81e88
size 1130978688

3
ai21labs_AI21-Jamba2-3B-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7e449d88575e025b5087da0fa6bb47c2e6f0089c1cb6c8803f8bc75d90291334
size 1465360768

3
ai21labs_AI21-Jamba2-3B-IQ3_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5be9246ef423acbf52727afaf527e69e7caeca4088227af062b816804f6d468c
size 1413244288

3
ai21labs_AI21-Jamba2-3B-IQ3_XXS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b80495a1c32738c94b54df5fb6c7704c852eabc1d402aa6b740570639efd984a
size 1299662208

3
ai21labs_AI21-Jamba2-3B-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e4d6b3a3df94c6c92d4e63bcb997cc85d99a3396b9b0b2fc3761a68ca553f47b
size 1854255488

3
ai21labs_AI21-Jamba2-3B-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:136e2fa1a913f9c94d42012f87099420cedb528a3997d83ab9b83a8e437fc7d3
size 1760354688

3
ai21labs_AI21-Jamba2-3B-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac179c7ff43868d43e544b66ac5079c126fe1ef8d1ae11ccc56ad14e25c7350d
size 1211035008

3
ai21labs_AI21-Jamba2-3B-Q2_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c0d9786605b858ce94c44dd3c4cf4a76515a432809b91d38aca0a80d6681b1e2
size 1374875008

3
ai21labs_AI21-Jamba2-3B-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ae50495f7eb08803df61bd07994646e29f73d3e6ac3c8a4a940dded75d9bcbc
size 1610113408

3
ai21labs_AI21-Jamba2-3B-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4d7de0c1c89c751a54efd858ddfb80cfde4dffec582c9bd9fe47b139583eaee
size 1537696128

3
ai21labs_AI21-Jamba2-3B-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b0fb7dc388d44ef2e84c9491c09a91174a2607f9069ce1aa12d97f8b98002029
size 1455177088

3
ai21labs_AI21-Jamba2-3B-Q3_K_XL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fe22d48907f35048217db2cedf729145d61315fc7f9e33c04d8907e978c255d2
size 1756914048

3
ai21labs_AI21-Jamba2-3B-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24cf1839927e02d8b4efa014bf766698a740e3d0b5f0958cb81d7e6715f7502c
size 1858187648

3
ai21labs_AI21-Jamba2-3B-Q4_1.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e29bc061ad0ff298071c07a8d7b81a3dd8381afb9916cd83de7ccb920d4a923e
size 2043388288

3
ai21labs_AI21-Jamba2-3B-Q4_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0fb0b377222f2a865ee88f11c73a9650817ff3cadef925e23a45dea17dadcf1c
size 2057214848

3
ai21labs_AI21-Jamba2-3B-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fa0876fa152f38689cefd6d498907d6255cf515780d65b16346d3190df6a0794
size 1932696448

3
ai21labs_AI21-Jamba2-3B-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:05e361b42b89c4d315a67b25a37e81bceedbfc27cb99b61cbba22e8fbfda56bc
size 1864864128

3
ai21labs_AI21-Jamba2-3B-Q5_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f9e269bb5030d895dabae4898aed7831a2a90c53357a4e7f14e6a864559adb2
size 2376436608

3
ai21labs_AI21-Jamba2-3B-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a55643e2f70b3000542d41f5003dd57f512f8506f816ff1dd9c758ed6fcd916b
size 2272889728

3
ai21labs_AI21-Jamba2-3B-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9f818e1247b159cb666714bf8e3499abe234b780a0a8e5686becc750c8bb984f
size 2233852288

3
ai21labs_AI21-Jamba2-3B-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf1628802987516f105893df8f9c2cd6e3eddc3a39046d463cfe6247897dc9b7
size 2639586688

3
ai21labs_AI21-Jamba2-3B-Q6_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d428ea6e819493d787e4f9902c6bcd54595923bddfc4177eb9675b2ee9691bbf
size 2720851328

3
ai21labs_AI21-Jamba2-3B-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2c624f1d663d2d9e1008d718c3e8d67ae62a19733ddde89ee90872e0c84eb50b
size 3407950208

3
ai21labs_AI21-Jamba2-3B-bf16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8d1bfd86cdb47739ab0996a89ccece1845648dfafa273d20a4cb060c748bd1e
size 6402228320

3
ai21labs_AI21-Jamba2-3B-imatrix.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef2c5d9418698424e05f429d64b96eb2746ca009e6fcc785d1925c9bf8d5a599
size 2950624

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}