Downloads · 30 days
157
1% of all-time downloads
HuggingFaceH4_-_mistral-7b-grok-gguf
RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf
HuggingFaceH4_-_mistral-7b-grok-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
21.8K
Public
Repo size
74.5 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.gguf87.5 GB · 100%
At a glance
- Access
- Public
- Created
- May 1, 2024
- Updated
- May 1, 2024
- SHA
- 60f26fb4
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
mistral-7b-grok - GGUF
- Model creator: https://huggingface.co/HuggingFaceH4/
- Original model: https://huggingface.co/HuggingFaceH4/mistral-7b-grok/
| Name | Quant method | Size |
|---|---|---|
| mistral-7b-grok.Q2_K.gguf | Q2_K | 2.53GB |
| mistral-7b-grok.IQ3_XS.gguf | IQ3_XS | 2.81GB |
| mistral-7b-grok.IQ3_S.gguf | IQ3_S | 2.96GB |
| mistral-7b-grok.Q3_K_S.gguf | Q3_K_S | 2.95GB |
| mistral-7b-grok.IQ3_M.gguf | IQ3_M | 3.06GB |
| mistral-7b-grok.Q3_K.gguf | Q3_K | 3.28GB |
| mistral-7b-grok.Q3_K_M.gguf | Q3_K_M | 3.28GB |
| mistral-7b-grok.Q3_K_L.gguf | Q3_K_L | 3.56GB |
| mistral-7b-grok.IQ4_XS.gguf | IQ4_XS | 3.67GB |
| mistral-7b-grok.Q4_0.gguf | Q4_0 | 3.83GB |
| mistral-7b-grok.IQ4_NL.gguf | IQ4_NL | 3.87GB |
| mistral-7b-grok.Q4_K_S.gguf | Q4_K_S | 3.86GB |
| mistral-7b-grok.Q4_K.gguf | Q4_K | 4.07GB |
| mistral-7b-grok.Q4_K_M.gguf | Q4_K_M | 4.07GB |
| mistral-7b-grok.Q4_1.gguf | Q4_1 | 4.24GB |
| mistral-7b-grok.Q5_0.gguf | Q5_0 | 4.65GB |
| mistral-7b-grok.Q5_K_S.gguf | Q5_K_S | 4.65GB |
| mistral-7b-grok.Q5_K.gguf | Q5_K | 4.78GB |
| mistral-7b-grok.Q5_K_M.gguf | Q5_K_M | 4.78GB |
| mistral-7b-grok.Q5_1.gguf | Q5_1 | 5.07GB |
| mistral-7b-grok.Q6_K.gguf | Q6_K | 5.53GB |
Original model description:
license: apache-2.0 base_model: mistralai/Mistral-7B-v0.1 tags:
- alignment-handbook
- generated_from_trainer datasets:
- HuggingFaceH4/grok-conversation-harmless
- HuggingFaceH4/ultrachat_200k model-index:
- name: mistral-7b-grok results: []
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Mistral 7B Grok
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 that has been aligned via Constitutional AI to mimic the style of xAI's Grok assistant.
It achieves the following results on the evaluation set:
- Loss: 0.9348
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9326 | 1.0 | 545 | 0.9348 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Created
- May 1, 2024
- Updated
- May 1, 2024