Downloads · 30 days
205
8% of all-time downloads
optimum_-_mistral-1.1b-testing-gguf
RichardErkhov/optimum_-_mistral-1.1b-testing-gguf
optimum_-_mistral-1.1b-testing-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
2.6K
Public
Repo size
12.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf14.7 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 3, 2024
- Updated
- Jul 3, 2024
- SHA
- 9160f3cd
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
mistral-1.1b-testing - GGUF
- Model creator: https://huggingface.co/optimum/
- Original model: https://huggingface.co/optimum/mistral-1.1b-testing/
| Name | Quant method | Size |
|---|---|---|
| mistral-1.1b-testing.Q2_K.gguf | Q2_K | 0.4GB |
| mistral-1.1b-testing.IQ3_XS.gguf | IQ3_XS | 0.44GB |
| mistral-1.1b-testing.IQ3_S.gguf | IQ3_S | 0.47GB |
| mistral-1.1b-testing.Q3_K_S.gguf | Q3_K_S | 0.47GB |
| mistral-1.1b-testing.IQ3_M.gguf | IQ3_M | 0.48GB |
| mistral-1.1b-testing.Q3_K.gguf | Q3_K | 0.51GB |
| mistral-1.1b-testing.Q3_K_M.gguf | Q3_K_M | 0.51GB |
| mistral-1.1b-testing.Q3_K_L.gguf | Q3_K_L | 0.55GB |
| mistral-1.1b-testing.IQ4_XS.gguf | IQ4_XS | 0.57GB |
| mistral-1.1b-testing.Q4_0.gguf | Q4_0 | 0.59GB |
| mistral-1.1b-testing.IQ4_NL.gguf | IQ4_NL | 0.6GB |
| mistral-1.1b-testing.Q4_K_S.gguf | Q4_K_S | 0.6GB |
| mistral-1.1b-testing.Q4_K.gguf | Q4_K | 0.62GB |
| mistral-1.1b-testing.Q4_K_M.gguf | Q4_K_M | 0.62GB |
| mistral-1.1b-testing.Q4_1.gguf | Q4_1 | 0.65GB |
| mistral-1.1b-testing.Q5_0.gguf | Q5_0 | 0.71GB |
| mistral-1.1b-testing.Q5_K_S.gguf | Q5_K_S | 0.71GB |
| mistral-1.1b-testing.Q5_K.gguf | Q5_K | 0.73GB |
| mistral-1.1b-testing.Q5_K_M.gguf | Q5_K_M | 0.73GB |
| mistral-1.1b-testing.Q5_1.gguf | Q5_1 | 0.77GB |
| mistral-1.1b-testing.Q6_K.gguf | Q6_K | 0.84GB |
| mistral-1.1b-testing.Q8_0.gguf | Q8_0 | 1.09GB |
Original model description:
license: apache-2.0
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
(model card is repeated due to open llm leaderboard length requirements)
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
mistralized tinyllama since flash attention training on llama w/ flash-attn is buggy.
it's based on the 3t base model (not chat tuned).
not extensively tested.
enjoy!
- Created
- Jul 3, 2024
- Updated
- Jul 3, 2024