huggingface / huggingface/candle

stabilityai/stablelm-2-zephyr-1_6b cannot fetch tokenizer.json

Open
#1,653 5 comments 1 reaction 0 assignees View on GitHub
Dominant language
Rust
Stars
21k
Forks
1.8k
Avg merge
16h 42m
Merged PRs (30d)
25

Description

After building release version **stable-lm** example, I get this issue:

```
./stable-lm --cpu --use-flash-attn --temperature 0.8 --top-p 40 -n 512 --which v2-zephyr --prompt "Build me website in 10 steps:"
avx: true, neon: false, simd128: false, f16c: true
temp: 0.80 repeat-penalty: 1.10 repeat-last-n: 64
Error: request error: https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b/resolve/main/tokenizer.json: status code 404

Caused by:
https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b/resolve/main/tokenizer.json: status code 404
```

There is not **tokenizer.json** file uploaded at https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b/tree/main

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the stable-lm example and the model-loading request for https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b/resolve/main/tokenizer.json. Verify how the example handles the reported 404 and determine what successful tokenizer loading should look like for this model; the issue provides no file or test path to run.

Written by the indexing model from the issue text.

Assessment

Tech stack
huggingface, rust
Domain
machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.