Paris99 commited on
Commit
012fdec
路
verified 路
1 Parent(s): 5551263

Card: remove GGUF links (GGUF builds not published yet)

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -33,7 +33,7 @@ Agreement with SenseNova's own PyTorch code (Transformers 5.18, bf16) on 16 prom
33
  | **[4-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-4bit)** (this repo) | 5.1 GB | 84.0% | 0.0982 | 2 / 16 |
34
  | [bf16](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-bf16) | 17.9 GB | 98.6% | 0.0012 | 12 / 16 |
35
 
36
- At 4 bits this build follows the original less closely than the larger ones. For the closest match on a small budget use the [6-bit build](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-6bit) or the [Q4_K_M GGUF](https://huggingface.co/netprojects/SenseNova-Loop-9B-GGUF).
37
 
38
  **Checks on this port:** 6-bit, 8-bit, 4-bit, bf16 builds answered short test prompts correctly with thinking on and off, and the 6-bit build found a pass code hidden in a 64K-token prompt.
39
 
@@ -75,7 +75,7 @@ print(generate(model, tokenizer, prompt=prompt, max_tokens=256))
75
 
76
  Set `enable_thinking=True` for thinking mode. Server: `mlx_lm.server --model netprojects/SenseNova-Loop-9B-MLX-4bit --trust-remote-code`.
77
 
78
- **Other formats:** [MLX 6-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-6bit) (7.3 GB) 路 [MLX 8-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-8bit) (9.5 GB) 路 [MLX bf16](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-bf16) (17.9 GB) 路 [GGUF for llama.cpp](https://huggingface.co/netprojects/SenseNova-Loop-9B-GGUF) (Q8_0 / Q6_K / Q4_K_M / BF16)
79
 
80
  ## License
81
 
 
33
  | **[4-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-4bit)** (this repo) | 5.1 GB | 84.0% | 0.0982 | 2 / 16 |
34
  | [bf16](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-bf16) | 17.9 GB | 98.6% | 0.0012 | 12 / 16 |
35
 
36
+ At 4 bits this build follows the original less closely than the larger ones. For the closest match on a small budget use the [6-bit build](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-6bit).
37
 
38
  **Checks on this port:** 6-bit, 8-bit, 4-bit, bf16 builds answered short test prompts correctly with thinking on and off, and the 6-bit build found a pass code hidden in a 64K-token prompt.
39
 
 
75
 
76
  Set `enable_thinking=True` for thinking mode. Server: `mlx_lm.server --model netprojects/SenseNova-Loop-9B-MLX-4bit --trust-remote-code`.
77
 
78
+ **Other formats:** [MLX 6-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-6bit) (7.3 GB) 路 [MLX 8-bit](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-8bit) (9.5 GB) 路 [MLX bf16](https://huggingface.co/netprojects/SenseNova-Loop-9B-MLX-bf16) (17.9 GB)
79
 
80
  ## License
81