Upload model
Browse files- .gitattributes +22 -0
- README.md +34 -0
- config.json +26 -0
- devstralsmall-2505-afq2-0.uqff +3 -0
- devstralsmall-2505-afq3-0.uqff +3 -0
- devstralsmall-2505-afq4-0.uqff +3 -0
- devstralsmall-2505-afq4-1.uqff +3 -0
- devstralsmall-2505-afq6-0.uqff +3 -0
- devstralsmall-2505-afq6-1.uqff +3 -0
- devstralsmall-2505-afq8-0.uqff +3 -0
- devstralsmall-2505-afq8-1.uqff +3 -0
- devstralsmall-2505-afq8-2.uqff +3 -0
- devstralsmall-2505-f8e4m3-0.uqff +3 -0
- devstralsmall-2505-f8e4m3-1.uqff +3 -0
- devstralsmall-2505-f8e4m3-2.uqff +3 -0
- devstralsmall-2505-q2k-0.uqff +3 -0
- devstralsmall-2505-q3k-0.uqff +3 -0
- devstralsmall-2505-q4k-0.uqff +3 -0
- devstralsmall-2505-q4k-1.uqff +3 -0
- devstralsmall-2505-q5k-0.uqff +3 -0
- devstralsmall-2505-q5k-1.uqff +3 -0
- devstralsmall-2505-q8_0-0.uqff +3 -0
- devstralsmall-2505-q8_0-1.uqff +3 -0
- devstralsmall-2505-q8_0-2.uqff +3 -0
- generation_config.json +6 -0
- residual.safetensors +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,25 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
devstralsmall-2505-afq2-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
devstralsmall-2505-afq3-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
devstralsmall-2505-afq4-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
devstralsmall-2505-afq4-1.uqff filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
devstralsmall-2505-afq6-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
devstralsmall-2505-afq6-1.uqff filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
devstralsmall-2505-afq8-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
devstralsmall-2505-afq8-1.uqff filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
devstralsmall-2505-afq8-2.uqff filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
devstralsmall-2505-f8e4m3-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
devstralsmall-2505-f8e4m3-1.uqff filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
devstralsmall-2505-f8e4m3-2.uqff filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
devstralsmall-2505-q2k-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
devstralsmall-2505-q3k-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
devstralsmall-2505-q4k-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
devstralsmall-2505-q4k-1.uqff filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
devstralsmall-2505-q5k-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
devstralsmall-2505-q5k-1.uqff filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
devstralsmall-2505-q8_0-0.uqff filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
devstralsmall-2505-q8_0-1.uqff filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
devstralsmall-2505-q8_0-2.uqff filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- uqff
|
| 4 |
+
- mistral.rs
|
| 5 |
+
base_model: mistralai/Devstral-Small-2505
|
| 6 |
+
base_model_relation: quantized
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- Autogenerated from user input. -->
|
| 10 |
+
|
| 11 |
+
# `mistralai/Devstral-Small-2505`, UQFF quantization
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
Run with [mistral.rs](https://github.com/EricLBuehler/mistral.rs). Documentation: [UQFF docs](https://github.com/EricLBuehler/mistral.rs/blob/master/docs/UQFF.md).
|
| 15 |
+
|
| 16 |
+
1) **Flexible** 🌀: Multiple quantization formats in *one* file format with *one* framework to run them all.
|
| 17 |
+
2) **Reliable** 🔒: Compatibility ensured with *embedded* and *checked* semantic versioning information from day 1.
|
| 18 |
+
3) **Easy** 🤗: Download UQFF models *easily* and *quickly* from Hugging Face, or use a local file.
|
| 19 |
+
3) **Customizable** 🛠️: Make and publish your own UQFF files in minutes.
|
| 20 |
+
|
| 21 |
+
## Examples
|
| 22 |
+
|Quantization type(s)|Example|
|
| 23 |
+
|--|--|
|
| 24 |
+
|AFQ2|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f devstralsmall-2505-afq2-0.uqff`|
|
| 25 |
+
|AFQ3|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f devstralsmall-2505-afq3-0.uqff`|
|
| 26 |
+
|AFQ4|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f "devstralsmall-2505-afq4-0.uqff;devstralsmall-2505-afq4-1.uqff"`|
|
| 27 |
+
|AFQ6|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f "devstralsmall-2505-afq6-0.uqff;devstralsmall-2505-afq6-1.uqff"`|
|
| 28 |
+
|AFQ8|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f "devstralsmall-2505-afq8-0.uqff;devstralsmall-2505-afq8-1.uqff;devstralsmall-2505-afq8-2.uqff"`|
|
| 29 |
+
|F8E4M3|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f "devstralsmall-2505-f8e4m3-0.uqff;devstralsmall-2505-f8e4m3-1.uqff;devstralsmall-2505-f8e4m3-2.uqff"`|
|
| 30 |
+
|Q2K|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f devstralsmall-2505-q2k-0.uqff`|
|
| 31 |
+
|Q3K|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f devstralsmall-2505-q3k-0.uqff`|
|
| 32 |
+
|Q4K|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f "devstralsmall-2505-q4k-0.uqff;devstralsmall-2505-q4k-1.uqff"`|
|
| 33 |
+
|Q5K|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f "devstralsmall-2505-q5k-0.uqff;devstralsmall-2505-q5k-1.uqff"`|
|
| 34 |
+
|Q8_0|`./mistralrs-server -i plain -m EricB/Devstral-Small-2505-UQFF -f "devstralsmall-2505-q8_0-0.uqff;devstralsmall-2505-q8_0-1.uqff;devstralsmall-2505-q8_0-2.uqff"`|
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"MistralForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"head_dim": 128,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 5120,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 32768,
|
| 13 |
+
"max_position_embeddings": 131072,
|
| 14 |
+
"model_type": "mistral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_hidden_layers": 40,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_theta": 1000000000.0,
|
| 20 |
+
"sliding_window": null,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.51.3",
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 131072
|
| 26 |
+
}
|
devstralsmall-2505-afq2-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d735e70d5d3899e9308bfe6f6982fec31f099ef8f2952535457bb670b8b6740d
|
| 3 |
+
size 7156572172
|
devstralsmall-2505-afq3-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6cd1b2840aea702bf8237739d928128b91368ad2c0993cde1e919e2a356faa00
|
| 3 |
+
size 10019184676
|
devstralsmall-2505-afq4-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:722add4105d994f8fcb61c9ceea6f76edcb9ced4946bcfb5b13b1519ade6ae2a
|
| 3 |
+
size 10723034840
|
devstralsmall-2505-afq4-1.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e4d2015a50d68471c7a9f2ec9795396faed966b5f236008b0daf3ed67900575
|
| 3 |
+
size 2158762404
|
devstralsmall-2505-afq6-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc418c0a92e11fcf0e61025611f3cabb2391189be4d75e3e0aa6bc2b16b011e2
|
| 3 |
+
size 10658143120
|
devstralsmall-2505-afq6-1.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:353de980fa8f998356127210d1e75f08f0a50562490e5081ec300c82867c4d61
|
| 3 |
+
size 7948879220
|
devstralsmall-2505-afq8-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c23660c25c577787bea511befac5b00ea5bf3871eed76e9589506004b2e0792a
|
| 3 |
+
size 10572940276
|
devstralsmall-2505-afq8-1.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a4aec6b68198c6aa4670ace0284c1fc7df00b55d755af60d927d97bfc66fe3b
|
| 3 |
+
size 10628647016
|
devstralsmall-2505-afq8-2.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0941df2e70f42cb6382b26c71200b5e56c4a4dcbe857fc0bf2f6a3835cf61923
|
| 3 |
+
size 3130660000
|
devstralsmall-2505-f8e4m3-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e130a00d349e921b6af17dd99d91dd48f4e11f5e5b0916a0e2f6327c33e0324c
|
| 3 |
+
size 10726948246
|
devstralsmall-2505-f8e4m3-1.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c68685bd133e914951d9669c64d298353e8c0068e8fbd868f575ee3e1b4ddb05
|
| 3 |
+
size 10726948716
|
devstralsmall-2505-f8e4m3-2.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee5b172c3e78715f57764152a47fb980b3cf5abcb52ac64537c254352260941e
|
| 3 |
+
size 1447036800
|
devstralsmall-2505-q2k-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60fc96007449b2dfccaca73f2ddffd9b3f035884f3690c41850d1da9a4b9cbd7
|
| 3 |
+
size 7514386938
|
devstralsmall-2505-q3k-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c10d89277c366387b9a8782e00198857c47c3a83b6d3fc8dce554ce7fc29693c
|
| 3 |
+
size 9840259594
|
devstralsmall-2505-q4k-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb64c3592d67315119817af1b79304a4311814ac9048ca0973ac0609b6fce5a7
|
| 3 |
+
size 10723024928
|
devstralsmall-2505-q4k-1.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf59f10e7dfda266877e16d2e248d23c682c5aa5d9c99d136d16dbd508179299
|
| 3 |
+
size 2158760514
|
devstralsmall-2505-q5k-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99c0b518276dd4af48158e7bd1c68503d020a95cc06aa5d57538105fa04ae412
|
| 3 |
+
size 10662071602
|
devstralsmall-2505-q5k-1.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:486d905329cfe78c2a57b735a04f57a85ec19f1addb70fe6d5c124f8ffefb2af
|
| 3 |
+
size 5082326440
|
devstralsmall-2505-q8_0-0.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7847a1c5499b5ffd72b800597597fe8b91482d342522f3fe6e2429d6a2bededa
|
| 3 |
+
size 10572935278
|
devstralsmall-2505-q8_0-1.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76189fcc3d670cc90dc8ee3ed5959446d14eb4de90ebd978ab8a59fb969ecee3
|
| 3 |
+
size 10628641724
|
devstralsmall-2505-q8_0-2.uqff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:314bc0fef18a622de3fe62202f4c7876add6c6438988b8b5f85d4b49c70bad61
|
| 3 |
+
size 3130658488
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.51.3"
|
| 6 |
+
}
|
residual.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:851804055704d0230e23c260cff884dbd4c107acf45114de6c2fc959c3c58c13
|
| 3 |
+
size 1343016224
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
| 3 |
+
size 17078037
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|