Downloads · 30 days
208
7% of all-time downloads
RichardErkhov/rhysjones_-_gpt2-774M-fineweb-150B-gguf
rhysjones_-_gpt2-774M-fineweb-150B-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.
Downloads · 30 days
208
7% of all-time downloads
All-time downloads
3K
Public
Repo size
10 GB
Likes
0
Public
Click a slice to open those files.
.gguf11.7 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
gpt2-774M-fineweb-150B - GGUF
| Name | Quant method | Size |
|---|---|---|
| gpt2-774M-fineweb-150B.Q2_K.gguf | Q2_K | 0.32GB |
| gpt2-774M-fineweb-150B.IQ3_XS.gguf | IQ3_XS | 0.36GB |
| gpt2-774M-fineweb-150B.IQ3_S.gguf | IQ3_S | 0.37GB |
| gpt2-774M-fineweb-150B.Q3_K_S.gguf | Q3_K_S | 0.37GB |
| gpt2-774M-fineweb-150B.IQ3_M.gguf | IQ3_M | 0.4GB |
| gpt2-774M-fineweb-150B.Q3_K.gguf | Q3_K | 0.43GB |
| gpt2-774M-fineweb-150B.Q3_K_M.gguf | Q3_K_M | 0.43GB |
| gpt2-774M-fineweb-150B.Q3_K_L.gguf | Q3_K_L | 0.46GB |
| gpt2-774M-fineweb-150B.IQ4_XS.gguf | IQ4_XS | 0.44GB |
| gpt2-774M-fineweb-150B.Q4_0.gguf | Q4_0 | 0.46GB |
| gpt2-774M-fineweb-150B.IQ4_NL.gguf | IQ4_NL | 0.47GB |
| gpt2-774M-fineweb-150B.Q4_K_S.gguf | Q4_K_S | 0.47GB |
| gpt2-774M-fineweb-150B.Q4_K.gguf | Q4_K | 0.51GB |
| gpt2-774M-fineweb-150B.Q4_K_M.gguf | Q4_K_M | 0.51GB |
| gpt2-774M-fineweb-150B.Q4_1.gguf | Q4_1 | 0.51GB |
| gpt2-774M-fineweb-150B.Q5_0.gguf | Q5_0 | 0.55GB |
| gpt2-774M-fineweb-150B.Q5_K_S.gguf | Q5_K_S | 0.55GB |
| gpt2-774M-fineweb-150B.Q5_K.gguf | Q5_K | 0.59GB |
| gpt2-774M-fineweb-150B.Q5_K_M.gguf | Q5_K_M | 0.59GB |
| gpt2-774M-fineweb-150B.Q5_1.gguf | Q5_1 | 0.6GB |
| gpt2-774M-fineweb-150B.Q6_K.gguf | Q6_K | 0.65GB |
| gpt2-774M-fineweb-150B.Q8_0.gguf | Q8_0 | 0.84GB |
license: mit datasets:
This is karpathy's model from the llm.c project converted to HF format to investigate bfloat16 performance.
The training run was 150B tokens, 1.5 epochs over the 100B FineWeb sample dataset.
There's active work underway at https://github.com/karpathy/llm.c so I'd suggest following the developments there!