Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+llama4-scout-instruct-q4k-0.uqff filter=lfs diff=lfs merge=lfs -text
+llama4-scout-instruct-q4k-1.uqff filter=lfs diff=lfs merge=lfs -text
+llama4-scout-instruct-q4k-2.uqff filter=lfs diff=lfs merge=lfs -text
+llama4-scout-instruct-q4k-3.uqff filter=lfs diff=lfs merge=lfs -text
+llama4-scout-instruct-q4k-4.uqff filter=lfs diff=lfs merge=lfs -text
+llama4-scout-instruct-q4k-5.uqff filter=lfs diff=lfs merge=lfs -text
+llama4-scout-instruct-q4k-6.uqff filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,28 @@
----
-license: mit
----
+---
+tags:
+  - uqff
+  - mistral.rs
+base_model: meta-llama/Llama-4-Scout-17B-16E-Instruct
+base_model_relation: quantized
+---
+
+<!-- Autogenerated from user input. -->
+
+# `meta-llama/Llama-4-Scout-17B-16E-Instruct`, UQFF quantization
+
+
+Run with [mistral.rs](https://github.com/EricLBuehler/mistral.rs). Documentation: [UQFF docs](https://github.com/EricLBuehler/mistral.rs/blob/master/docs/UQFF.md).
+
+1) **Flexible** 🌀: Multiple quantization formats in *one* file format with *one* framework to run them all.
+2) **Reliable** 🔒: Compatibility ensured with *embedded* and *checked* semantic versioning information from day 1.
+3) **Easy** 🤗: Download UQFF models *easily* and *quickly* from Hugging Face, or use a local file.
+3) **Customizable** 🛠️: Make and publish your own UQFF files in minutes.
+
+## Examples
+
+Note: If you are using an Apple Silicon device (on Metal), prefer using an 🔥 AFQ quantization for optimum performance!
+
+|Quantization type(s)|Example|
+|--|--|
+|Q4K|`./mistralrs-server -i vision-plain -m EricB/Llama-4-Scout-17B-16E-Instruct-UQFF -a llama4 --from-uqff "llama4-scout-instruct-q4k-0.uqff;llama4-scout-instruct-q4k-1.uqff;llama4-scout-instruct-q4k-2.uqff;llama4-scout-instruct-q4k-3.uqff;llama4-scout-instruct-q4k-4.uqff;llama4-scout-instruct-q4k-5.uqff;llama4-scout-instruct-q4k-6.uqff"`|
+|AFQ4 |Coming soon!|

config.json

@@ -0,0 +1,80 @@
+{
+  "architectures": [
+    "Llama4ForConditionalGeneration"
+  ],
+  "boi_token_index": 200080,
+  "eoi_token_index": 200081,
+  "image_token_index": 200092,
+  "model_type": "llama4",
+  "text_config": {
+    "_attn_implementation_autoset": true,
+    "attention_bias": false,
+    "attention_chunk_size": 8192,
+    "attention_dropout": 0.0,
+    "bos_token_id": 200000,
+    "eos_token_id": [
+      200001,
+      200007,
+      200008
+    ],
+    "for_llm_compressor": false,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "interleave_moe_layer_step": 1,
+    "intermediate_size": 8192,
+    "intermediate_size_mlp": 16384,
+    "max_position_embeddings": 10485760,
+    "model_type": "llama4_text",
+    "no_rope_layers": [],
+    "num_attention_heads": 40,
+    "num_experts_per_tok": 1,
+    "num_hidden_layers": 48,
+    "num_key_value_heads": 8,
+    "num_local_experts": 16,
+    "output_router_logits": false,
+    "pad_token_id": 200018,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 16.0,
+      "high_freq_factor": 1.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "use_qk_norm": true,
+    "vocab_size": 202048
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0.dev0",
+  "vision_config": {
+    "_attn_implementation_autoset": true,
+    "attention_dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1408,
+    "image_size": 336,
+    "initializer_range": 0.02,
+    "intermediate_size": 5632,
+    "model_type": "llama4_vision_model",
+    "multi_modal_projector_bias": false,
+    "norm_eps": 1e-05,
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 34,
+    "patch_size": 14,
+    "pixel_shuffle_ratio": 0.5,
+    "projector_dropout": 0.0,
+    "projector_input_dim": 4096,
+    "projector_output_dim": 4096,
+    "rope_theta": 10000,
+    "vision_feature_layer": -1,
+    "vision_feature_select_strategy": "default",
+    "vision_output_dim": 4096
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 200000,
+  "do_sample": true,
+  "eos_token_id": [
+    200001,
+    200007,
+    200008
+  ],
+  "pad_token_id": 200018,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.0.dev0"
+}

llama4-scout-instruct-q4k-0.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6cad10ce6f77ac322176c5caadfb4b2a2c5ef9e7a0b1134214a90cc36ef33f0
+size 11187399004

llama4-scout-instruct-q4k-1.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec14fb86ff33941f4bb0b0084e2156da3f9f9031f1a63123939d28d7feb1b92f
+size 10629093732

llama4-scout-instruct-q4k-2.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f7d19d8fdd825fbbc26c5164d39fe04dd031527204e17561c23cd0a5a9043b
+size 10711623460

llama4-scout-instruct-q4k-3.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a00012bbe2e499d6742ca557140e530f0f0936b1649371c18efa2cdcc01d844
+size 10629094212

llama4-scout-instruct-q4k-4.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6d50da30540606a3380e5b500d106880c7b5d88f5dc0d7432e046a3d21b4427
+size 10702776140

llama4-scout-instruct-q4k-5.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe27f9e454c98fafed7a546324c70e5bc4a40dc1651e7a297f9c5cc918ffd78
+size 6664625396

llama4-scout-instruct-q4k-6.uqff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a230dfd04529c488df5a3ec1b7292f0eaf71f2ac284c61f2796a285a6e040f15
+size 26879814

preprocessor_config.json

@@ -0,0 +1,33 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Llama4ImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_patches": 16,
+  "processor_class": "Llama4Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "resize_to_max_canvas": false,
+  "return_tensors": null,
+  "size": {
+    "height": 336,
+    "width": 336
+  }
+}

processor_config.json

@@ -0,0 +1,6 @@
+{
+  "fake_image_token": "<|image|>",
+  "image_token": "<|image|>",
+  "patch_size": 14,
+  "processor_class": "Llama4Processor"
+}

residual.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2530ffaf3baab074f01c4b0adb4c8127fa98af17b2ee0627482ee68e6b77f93d
+size 2115616688

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d98b584d0de067c4f8865975052b632d10e2e2aff6fcff80e8ec2f8e7990545f
+size 28011016