github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4706] 22B Codestral model #2966

New Issue
Closed
opened 2026-04-12 13:20:35 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 13:20:35 -05:00
Owner
Copy Link

Originally created by @DuckyBlender on GitHub (May 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4706

https://huggingface.co/mistralai/Codestral-22B-v0.1
https://mistral.ai/news/codestral/

Originally created by @DuckyBlender on GitHub (May 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4706 https://huggingface.co/mistralai/Codestral-22B-v0.1 https://mistral.ai/news/codestral/
GiteaMirror added the model label 2026-04-12 13:20:35 -05:00
GiteaMirror commented 2026-04-12 13:20:37 -05:00
Author
Owner
Copy Link

@MostWrong commented on GitHub (May 29, 2024):

trying to convert it into gguf rn!!

<!-- gh-comment-id:2137909002 --> @MostWrong commented on GitHub (May 29, 2024): trying to convert it into gguf rn!!
GiteaMirror commented 2026-04-12 13:20:38 -05:00
Author
Owner
Copy Link

@kernelzeroday commented on GitHub (May 29, 2024):

I was looking up quantization methods, Do you mind sharing your process you are using? What Quantization levels are you targeting? I am hoping for a full precision GGUF if possible, I can train myself if needed.

<!-- gh-comment-id:2137914342 --> @kernelzeroday commented on GitHub (May 29, 2024): I was looking up quantization methods, Do you mind sharing your process you are using? What Quantization levels are you targeting? I am hoping for a full precision GGUF if possible, I can train myself if needed.
GiteaMirror commented 2026-04-12 13:20:38 -05:00
Author
Owner
Copy Link

@kernelzeroday commented on GitHub (May 29, 2024):

For those seeking to recreate my steps:

huggingface-cli download --local-dir cst  mistralai/Codestral-22B-v0.1
cp cst/tokenizer.model.v3 cst/tokenizer.model

$ cat cst/config.json
{
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "sliding_window": null,
  "use_cache": true,

    "dim": 6144,
    "n_layers": 56,
    "head_dim": 128,
    "hidden_dim": 16384,
    "n_heads": 48,
    "n_kv_heads": 8,
    "norm_eps": 1e-05,
    "vocab_size": 32768,
    "rope_theta": 1000000.0
}

python llama.cpp/convert-hf-to-gguf.py --verbose cst/

INFO:hf-to-gguf:Model successfully exported to 'cst/ggml-model-f16.gguf'

enjoy

<!-- gh-comment-id:2138162785 --> @kernelzeroday commented on GitHub (May 29, 2024): For those seeking to recreate my steps: ``` huggingface-cli download --local-dir cst mistralai/Codestral-22B-v0.1 cp cst/tokenizer.model.v3 cst/tokenizer.model $ cat cst/config.json { "architectures": [ "MistralForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "mistral", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "sliding_window": null, "use_cache": true, "dim": 6144, "n_layers": 56, "head_dim": 128, "hidden_dim": 16384, "n_heads": 48, "n_kv_heads": 8, "norm_eps": 1e-05, "vocab_size": 32768, "rope_theta": 1000000.0 } python llama.cpp/convert-hf-to-gguf.py --verbose cst/ INFO:hf-to-gguf:Model successfully exported to 'cst/ggml-model-f16.gguf' ``` enjoy
GiteaMirror commented 2026-04-12 13:20:39 -05:00
Author
Owner
Copy Link

@DuckyBlender commented on GitHub (May 29, 2024):

https://ollama.com/library/codestral

<!-- gh-comment-id:2138171124 --> @DuckyBlender commented on GitHub (May 29, 2024): https://ollama.com/library/codestral
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label model
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2966
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?