Downloads · 30 days
29
3% of all-time downloads
SpectraSuite_-_FloatLM_1.5B-gguf
RichardErkhov/SpectraSuite_-_FloatLM_1.5B-gguf
SpectraSuite_-_FloatLM_1.5B-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
1K
Public
Repo size
17.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf20.3 GB · 100%
At a glance
- Access
- Public
- Created
- Oct 4, 2024
- Updated
- Oct 4, 2024
- SHA
- 3e68cbf2
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
FloatLM_1.5B - GGUF
- Model creator: https://huggingface.co/SpectraSuite/
- Original model: https://huggingface.co/SpectraSuite/FloatLM_1.5B/
| Name | Quant method | Size |
|---|---|---|
| FloatLM_1.5B.Q2_K.gguf | Q2_K | 0.56GB |
| FloatLM_1.5B.IQ3_XS.gguf | IQ3_XS | 0.62GB |
| FloatLM_1.5B.IQ3_S.gguf | IQ3_S | 0.65GB |
| FloatLM_1.5B.Q3_K_S.gguf | Q3_K_S | 0.65GB |
| FloatLM_1.5B.IQ3_M.gguf | IQ3_M | 0.68GB |
| FloatLM_1.5B.Q3_K.gguf | Q3_K | 0.71GB |
| FloatLM_1.5B.Q3_K_M.gguf | Q3_K_M | 0.71GB |
| FloatLM_1.5B.Q3_K_L.gguf | Q3_K_L | 0.77GB |
| FloatLM_1.5B.IQ4_XS.gguf | IQ4_XS | 0.78GB |
| FloatLM_1.5B.Q4_0.gguf | Q4_0 | 0.82GB |
| FloatLM_1.5B.IQ4_NL.gguf | IQ4_NL | 0.82GB |
| FloatLM_1.5B.Q4_K_S.gguf | Q4_K_S | 0.83GB |
| FloatLM_1.5B.Q4_K.gguf | Q4_K | 0.87GB |
| FloatLM_1.5B.Q4_K_M.gguf | Q4_K_M | 0.87GB |
| FloatLM_1.5B.Q4_1.gguf | Q4_1 | 0.9GB |
| FloatLM_1.5B.Q5_0.gguf | Q5_0 | 0.98GB |
| FloatLM_1.5B.Q5_K_S.gguf | Q5_K_S | 0.98GB |
| FloatLM_1.5B.Q5_K.gguf | Q5_K | 1.01GB |
| FloatLM_1.5B.Q5_K_M.gguf | Q5_K_M | 1.01GB |
| FloatLM_1.5B.Q5_1.gguf | Q5_1 | 1.07GB |
| FloatLM_1.5B.Q6_K.gguf | Q6_K | 1.16GB |
| FloatLM_1.5B.Q8_0.gguf | Q8_0 | 1.5GB |
Original model description:
license: apache-2.0
FloatLM 1.5B
The good ol' FP16 LLMs with LLaMa architecture.
import transformers as tf, torch
model_name = "SpectraSuite/FloatLM_1.5B"
# Please adjust the temperature, repetition penalty, top_k, top_p and other sampling parameters according to your needs.
pipeline = tf.pipeline("text-generation", model=model_id, model_kwargs={"torch_dtype": torch.float16}, device_map="auto")
# These are base (pretrained) LLMs that are not instruction and chat tuned. You may need to adjust your prompt accordingly.
pipeline("Once upon a time")
- License: Apache 2.0
- We will use our GitHub repo for communication (including HF repo related queries). Feel free to open an issue here https://github.com/NolanoOrg/SpectraSuite
- Created
- Oct 4, 2024
- Updated
- Oct 4, 2024