lmstudio-community/dolphin-2.8-mistral-7b-v02-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: lmstudio-community/dolphin-2.8-mistral-7b-v02-GGUF
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-18 11:02:14 +08:00
commit 921d4a801a
20 changed files with 280 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

51
.gitattributes vendored Normal file
View File

@@ -0,0 +1,51 @@
*.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
dolphin-2.8-mistral-7b-v02-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
dolphin-2.8-mistral-7b-v02-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

179
README.md Normal file
View File

@@ -0,0 +1,179 @@
---
base_model: alpindale/Mistral-7B-v0.2-hf
language:
- en
license: apache-2.0
datasets:
- cognitivecomputations/dolphin
- cognitivecomputations/dolphin-coder
- cognitivecomputations/samantha-data
- jondurbin/airoboros-2.2.1
- teknium/openhermes-2.5
- m-a-p/Code-Feedback
- m-a-p/CodeFeedback-Filtered-Instruction
model-index:
- name: dolphin-2.8-mistral-7b-v02
results:
- task:
type: text-generation
dataset:
type: openai_humaneval
name: HumanEval
metrics:
- name: pass@1
type: pass@1
value: 0.469
verified: false
quantized_by: bartowski
pipeline_tag: text-generation
lm_studio:
param_count: 7b
use_case: general
release_date: 28-03-2024
model_creator: cognitivecomputations
prompt_template: ChatML
system_prompt: You are Dolphin, a helpful AI assistant.
base_model: mistral
original_repo: cognitivecomputations/dolphin-2.8-mistral-7b-v02
---
## 💫 Community Model> Dolphin 2.8 Mistral 7b v0.2 🐬 by Cognitive Computations
*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
**Model creator:** [Cognitive Computations](https://huggingface.co/cognitivecomputations)<br>
**Original model**: [dolphin-2.8-mistral-7b-v02](https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02)<br>
**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b2536](https://github.com/ggerganov/llama.cpp/releases/tag/b2536)<br>
## Model Summary:
Dolphin 2.8 is a model from from the Dolphin family, based on Mistral 0.2, and fine tuned by [Eric Hartford](https://huggingface.co/ehartford/) and [Cognitive Computations](https://huggingface.co/cognitivecomputations).
With a broad range of uses, this model makes for a great general-use daily driver.<br>
## Prompt Template:
Choose the `ChatML` preset in your LM Studio.
Under the hood, the model will see a prompt that's formatted like so:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
```
## Use case and examples
Dolphin is trained on a vast variety of data, including conversational, logical, and coding. This unique blend, along with a keen eye from the model creators, makes for a wonderful model that can tackle any task you throw at it.
### General knowledge:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.
<|im_end|>
<|im_start|>user
What does the ISO number mean in camera terminology?<|im_end|>
<|im_start|>assistant
The ISO number in camera terminology refers to the camera's sensitivity to light. ISO stands for International Organization for Standardization. It is a measure of the luminous flux received by a sensor or film.
A higher ISO number means that the camera's sensor is more sensitive to light, allowing for faster shutter speeds in low-light situations. However, increasing the ISO also increases the risk of image noise (graininess) in the final image. Conversely, a lower ISO number means that the camera's sensor is less sensitive to light, requiring slower shutter speeds in well-lit conditions to avoid overexposure.
In summary, the ISO number in camera terminology determines how sensitive the camera's sensor is to light, and it can be adjusted to balance exposure and image quality in various lighting conditions.
```
### Conversational:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.
<|im_end|>
<|im_start|>user
What is the meaning of life, and how can I find my purpose?<|im_end|>
<|im_start|>assistant
The meaning of life is a subjective and philosophical question that has been debated for centuries. Different people have different perspectives on what gives life meaning, as it can vary greatly from person to person. Some people find meaning in their relationships, their work, or their spiritual beliefs.
To find your purpose, you can follow these steps:
1. Reflect on your passions and interests: Think about the things that genuinely excite you and make you feel alive. Consider what activities you enjoy and what subjects you find most interesting.
2. Explore your talents and strengths: Identify the skills and abilities you possess. You may have natural talents that you can develop and use to contribute to society.
3. Assess your values and principles: Reflect on your beliefs, moral compass, and personal code of conduct. Consider how your values can guide you in determining your purpose.
4. Set goals and objectives: Establish short-term and long-term goals that align with your passions, talents, and values. This will help you stay focused and motivated in your journey to find your purpose.
5. Take action and learn from experience: Begin to pursue the goals and objectives you've set, and learn from the experiences you encounter along the way. Embrace the process of self-discovery and growth.
6. Seek guidance and support: Share your journey with friends, family, or mentors who can offer valuable advice, encouragement, and resources to help you find your purpose.
Ultimately, finding your purpose is a personal and ongoing process that requires introspection, self-awareness, and a willingness to explore new opportunities. Remember, there is no one-size-fits-all answer to the meaning of life, and your purpose may change and evolve over time.
```
### Coding:
```
<|im_start|>system
You are Dolphin, a helpful AI assistant.
<|im_end|>
<|im_start|>user
I have a multi select component in react, and I register it to a useForm. I want to validate that there are no more than 10 items selected on submission. Is this possible?<|im_end|>
<|im_start|>assistant
Yes, it is possible to validate the number of selected items in a multi select component in React with the help of `useForm`. You can use the `validate` function from `react-hook-form` to achieve this. Here's a step-by-step guide on how to do it:
First, import the necessary libraries:
import { useForm } from 'react-hook-form';
import { MultiSelect } from 'your-multi-select-component';
Next, create a form with the multi select component:
function MyForm() {
const { register, handleSubmit, errors } = useForm();
const onSubmit = data => {
// Handle form submission logic here
};
return (
<form onSubmit={handleSubmit(onSubmit)}>
<MultiSelect
name="multiSelect"
ref={register({ required: true, validate: value => value.length <= 10 })}
/>
{errors.multiSelect && (
<p>Please select no more than 10 items.</p>
)}
<input type="submit" />
</form>
);
}
In the above code, we register the multi select component with the `useForm` hook. The `validate` function is used to validate that the number of selected items is less than or equal to 10. If the validation fails, an error message will be displayed.
Remember to replace `'your-multi-select-component'` with the name of your multi select component.
That's it! Now, when the form is submitted, it will validate that no more than 10 items are selected in the multi select component.
```
## Technical Details
This model was trained with the following datasets:
- [cognitivecomputations/dolphin](https://huggingface.co/datasets/cognitivecomputations/dolphin)
- [cognitivecomputations/dolphin-coder](https://huggingface.co/datasets/cognitivecomputations/dolphin-coder)
- [cognitivecomputations/samantha-data](https://huggingface.co/datasets/cognitivecomputations/samantha-data)
- [jondurbin/airoboros-2.2.1](https://huggingface.co/datasets/jondurbin/airoboros-2.2.1)
- [teknium/openhermes-2.5](https://huggingface.co/datasets/teknium/openhermes-2.5)
- [m-a-p/Code-Feedback](https://huggingface.co/datasets/m-a-p/Code-Feedback)
- [m-a-p/CodeFeedback-Filtered-Instruction](https://huggingface.co/datasets/m-a-p/CodeFeedback-Filtered-Instruction)
## Special thanks
🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
## Disclaimers
LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model. You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models. LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.

1
configuration.json Normal file
View File

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

3
dolphin-2.8-mistral-7b-v02-IQ3_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0f55e37c371b25266fd9d06d3f2504a66742c35c843ec4f7bfa5c4a833ace6eb
size 3284901952

3
dolphin-2.8-mistral-7b-v02-IQ3_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:cf5cc4eb6689acb5b609750443af6066461f20302be89551e6361f4f48a8d2ab
size 3182403648

3
dolphin-2.8-mistral-7b-v02-IQ4_NL.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:396b28d5ba48da0a4d4d3d564b1793c8c0721b404ec3bde2cbed9f0944370c10
size 4155065472

3
dolphin-2.8-mistral-7b-v02-IQ4_XS.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef64d88e5a6461d0705f7cc436cfd19dd3305ee5310ea5091f2716af6706d435
size 3944399744

3
dolphin-2.8-mistral-7b-v02-Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:47973d42442cda21d9acd66fdc0231ff4698a0982346d83681967dd5c39c9a72
size 2719251712

3
dolphin-2.8-mistral-7b-v02-Q3_K_L.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a16b72d1962f9b6702f85dffa45a110ee1c12d5e3cb297de43701e422b536d4a
size 3822035008

3
dolphin-2.8-mistral-7b-v02-Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:06f1917ccca147f426fd5810f975829cf9822170c607a13003bbf28e8aaf5ccf
size 3518996544

3
dolphin-2.8-mistral-7b-v02-Q3_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:88d8f60d8f50190d3ef0085c0ced9fabe04bd5c8c18b3840e48f640100c5dbbf
size 3164577856

3
dolphin-2.8-mistral-7b-v02-Q4_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e7eb0add3f5bde0d4f35e878d1fe8f547fb5d909035d76b66c0e87c30163785c
size 4108928128

3
dolphin-2.8-mistral-7b-v02-Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:acf5681de049fe3c2486def0e744089b6d1894cf613700386c9d5c17a3a07412
size 4368450688

3
dolphin-2.8-mistral-7b-v02-Q4_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4b9796ca246ef8bd0a2409a662592be63e687597e0988e9444b14f879c7682b
size 4140385408

3
dolphin-2.8-mistral-7b-v02-Q5_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7a0142ed0da77ad5ffb53e5429c92992c6b88c4ea2d1e146372282dbe3b1e946
size 4997728384

3
dolphin-2.8-mistral-7b-v02-Q5_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:063751ffeadf1e692432e7b1b288e51fb32db0bde86abc09f26850ab05a50f92
size 5131421824

3
dolphin-2.8-mistral-7b-v02-Q5_K_S.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:974647f39d67f422186d520f036b665b46e082e1632e131cf6aabd363a1e9c78
size 4997728384

3
dolphin-2.8-mistral-7b-v02-Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:40037a7b7796f8d97270d96570531a32d6197f22dd8c37a60ba5fe84ef415276
size 5942078656

3
dolphin-2.8-mistral-7b-v02-Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:49d60b64563d5e4e78211eb3dfb1af75c3c89d1158f141bc0bf38ec5eac30fbb
size 7695875136

1
original_repo_url.txt Normal file
View File

@@ -0,0 +1 @@
https://huggingface.co/bartowski/dolphin-2.8-mistral-7b-v02-GGUF