Sponsored by PoYo.AI
Toolify Toolify logo
AI Models
Vicuna-7B-v1.3-ggml

localmodels / Vicuna-7B-v1.3-ggml

Run on huggingface.co
huggingface.co
Total runs: 0
24-hour runs: 0
7-day runs: 0
30-day runs: 0
Model's Last Updated: July 12 2023

Introduction of Vicuna-7B-v1.3-ggml

Model Details of Vicuna-7B-v1.3-ggml

Vicuna 7B v1.3 ggml

From LMSYS: https://huggingface.co/lmsys/vicuna-7b-v1.3

Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0

Quantized using an older version of llama.cpp and compatible with llama.cpp from May 19, commit 2d5db48.

k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K

Quantization methods compatible with latest llama.cpp from June 6, commit 2d43387.

Files
Name Quant method Bits Size Max RAM required, no GPU offloading Use case
vicuna-7b-v1.3.ggmlv3.q2_K.bin q2_K 2 2.87 GB 5.37 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors.
vicuna-7b-v1.3.ggmlv3.q3_K_L.bin q3_K_L 3 3.60 GB 6.10 GB New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
vicuna-7b-v1.3.ggmlv3.q3_K_M.bin q3_K_M 3 3.28 GB 5.78 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
vicuna-7b-v1.3.ggmlv3.q3_K_S.bin q3_K_S 3 2.95 GB 5.45 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
vicuna-7b-v1.3.ggmlv3.q4_0.bin q4_0 4 3.79 GB 6.29 GB Original llama.cpp quant method, 4-bit.
vicuna-7b-v1.3.ggmlv3.q4_1.bin q4_1 4 4.21 GB 6.71 GB Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
vicuna-7b-v1.3.ggmlv3.q4_K_M.bin q4_K_M 4 4.08 GB 6.58 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K
vicuna-7b-v1.3.ggmlv3.q4_K_S.bin q4_K_S 4 3.83 GB 6.33 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
vicuna-7b-v1.3.ggmlv3.q5_0.bin q5_0 5 4.63 GB 7.13 GB Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
vicuna-7b-v1.3.ggmlv3.q5_1.bin q5_1 5 5.06 GB 7.56 GB Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
vicuna-7b-v1.3.ggmlv3.q5_K_M.bin q5_K_M 5 4.78 GB 7.28 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K
vicuna-7b-v1.3.ggmlv3.q5_K_S.bin q5_K_S 5 4.65 GB 7.15 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
vicuna-7b-v1.3.ggmlv3.q6_K.bin q6_K 6 5.53 GB 8.03 GB New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors
vicuna-7b-v1.3.ggmlv3.q8_0.bin q8_0 8 7.16 GB 9.66 GB Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

Vicuna Model Card

Model Details

Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT.

  • Developed by: LMSYS
  • Model type: An auto-regressive language model based on the transformer architecture.
  • License: Non-commercial license
  • Finetuned from model: LLaMA .
Model Sources
Uses

The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.

How to Get Started with the Model

Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights .
APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api .

Training Details

Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning. The training data is around 140K conversations collected from ShareGPT.com. See more details in the "Training Details of Vicuna Models" section in the appendix of this paper .

Evaluation

Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this paper .

Difference between different versions of Vicuna

See vicuna_weights_version.md

Runs of localmodels Vicuna-7B-v1.3-ggml on huggingface.co

0
Total runs
0
24-hour runs
0
3-day runs
0
7-day runs
0
30-day runs

More Information About Vicuna-7B-v1.3-ggml huggingface.co Model

Vicuna-7B-v1.3-ggml huggingface.co

Vicuna-7B-v1.3-ggml huggingface.co is an AI model on huggingface.co that provides Vicuna-7B-v1.3-ggml's model effect (), which can be used instantly with this localmodels Vicuna-7B-v1.3-ggml model. huggingface.co supports a free trial of the Vicuna-7B-v1.3-ggml model, and also provides paid use of the Vicuna-7B-v1.3-ggml. Support call Vicuna-7B-v1.3-ggml model through api, including Node.js, Python, http.

Vicuna-7B-v1.3-ggml huggingface.co Url

https://huggingface.co/localmodels/Vicuna-7B-v1.3-ggml

localmodels Vicuna-7B-v1.3-ggml online free

Vicuna-7B-v1.3-ggml huggingface.co is an online trial and call api platform, which integrates Vicuna-7B-v1.3-ggml's modeling effects, including api services, and provides a free online trial of Vicuna-7B-v1.3-ggml, you can try Vicuna-7B-v1.3-ggml online for free by clicking the link below.

localmodels Vicuna-7B-v1.3-ggml online free url in huggingface.co:

https://huggingface.co/localmodels/Vicuna-7B-v1.3-ggml

Vicuna-7B-v1.3-ggml install

Vicuna-7B-v1.3-ggml is an open source model from GitHub that offers a free installation service, and any user can find Vicuna-7B-v1.3-ggml on GitHub to install. At the same time, huggingface.co provides the effect of Vicuna-7B-v1.3-ggml install, users can directly use Vicuna-7B-v1.3-ggml installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Vicuna-7B-v1.3-ggml install url in huggingface.co:

https://huggingface.co/localmodels/Vicuna-7B-v1.3-ggml

Url of Vicuna-7B-v1.3-ggml

Vicuna-7B-v1.3-ggml huggingface.co Url

Provider of Vicuna-7B-v1.3-ggml huggingface.co

localmodels
ORGANIZATIONS
huggingface.co

Other API from localmodels