Converted ./Llama-4-Maverick-17B-128E-Linearized to BNB with nf4 and bf16

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}    \n    {%- if messages[0]['content'] is string %}\n        {%- set system_message = messages[0]['content']|trim %}\n    {%- else %}\n        {#- FIXME: The processor requires an array, always. #}\n        {%- set system_message = messages[0]['content'][0]['text']|trim %}\n    {%- endif %}\n    {%- set messages = messages[1:] %}\n    {%- set user_supplied_system_message = true %}\n{%- else %}\n    {%- set system_message = \"\" %}\n    {%- set user_supplied_system_message = false %}\n{%- endif %}\n\n{#- System message if the user supplied one #}\n{%- if user_supplied_system_message %}\n    {{- \"<|header_start|>system<|header_end|>\n\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\n\" }}\n    {%- endif %}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\n\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\n\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|header_start|>user<|header_end|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|header_start|>' + message['role'] + '<|header_end|>\n\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}\n       {{- '<|header_start|>assistant<|header_end|>\n\n' -}}\n       {{- '<|python_start|>' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n       {{- '<|python_end|>' }}\n        {%- for tool_call in message.tool_calls %}\n           {{- '{\"name\": \"' + tool_call.function.name + '\", ' }}\n           {{- '\"parameters\": ' }}\n           {{- tool_call.function.arguments | tojson }}\n           {{- \"}\" }}\n        {%- endfor %}\n       {{- \"<|eot|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|header_start|>ipython<|header_end|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|header_start|>assistant<|header_end|>\n\n' }}\n{%- endif %}\n"
+}

config.json

@@ -0,0 +1,83 @@
+{
+  "architectures": [
+    "Llama4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": 4,
+  "bos_token_id": 200000,
+  "eos_token_id": 200001,
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 2,
+  "intermediate_size": 8192,
+  "intermediate_size_mlp": 16384,
+  "max_position_embeddings": 262144,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    1,
+    3,
+    5,
+    7,
+    9,
+    11,
+    13,
+    15,
+    17,
+    19,
+    21,
+    23,
+    25,
+    27,
+    29,
+    31,
+    33,
+    35,
+    37,
+    39,
+    41,
+    43,
+    45,
+    47
+  ],
+  "no_rope_layers": 4,
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "pad_token_id": 200018,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.0",
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 202048
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 200000,
+  "eos_token_id": 200001,
+  "pad_token_id": 200018,
+  "transformers_version": "4.51.0"
+}

model-00001-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a13110f59602845defca4898dac0703c01c2619ffd206c216b97c2338cb65d
+size 4990289311

model-00002-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9535255b9bf2d039d13bea3bc718517844e5eec1b8f6bb9381478d092e76d7
+size 4998657065

model-00003-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc89ba38a15e90c37dc2029d01466e2c4fbe16459aa119930611703794697280
+size 4999042575

model-00004-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8a770529bdd0673f497d19230628a32dbbd46741d4397ac7083e7d961c2641f
+size 4999042613

model-00005-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee043017a34fb2e5e643885350d12bf3cd37ca09bbc0bca9b6033fa0a35b6347
+size 4998657261

model-00006-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a340c957cd75b9bafcddb24d40ebb97856cb67e6550c18fc19d41bf9097393c
+size 4999043213

model-00007-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d48f39b16086bf857f821a65c8e36dcc8fc010d476bb3211ba26935d01a056
+size 4998657217

model-00008-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff27415ac0f2254273c7c3c3016372026ffea0614ead7b9fd4cba20b6c1e4a00
+size 4999042994

model-00009-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76083dbe9f3d327777da4667ec6151d7c5dbe58a7ebc67bb38272a1929ac396e
+size 4966564401

model-00010-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a6bcb9fd97fad0b00fe58c0ddeb69f510bd857719ea2ba9b2461207730b4755
+size 4987858255

model-00011-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cb754c44232e6443a4dc7fa7f7e9c833f45d07db55a845603b6f5dbb1bd00a3
+size 4999044384

model-00012-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5acf4a89594b8ab78521e925f487423303c7d7426983c67d925aa54ae0f6b43b
+size 4998658594

model-00013-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a3e4abe6493908c96e36e744d3b4fa226a2cc544feb832c2af24f6cb63e085
+size 4999044817

model-00014-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be599e20500a2c032aa3082aa43aee4fd4b03ed747fe14303ffefa8d990d51af
+size 4998658454

model-00015-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9045c54df0afbad6f3f2720a41a1bb2571595b74ed3c2bf575ef51e677281f62
+size 4999044022

model-00016-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9ecb62fb47b2244022aa60f0c449086ad9312a31c3d9ad09ae7dfcf2def722
+size 4999043993

model-00017-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2130b465e514cd3b3682f0bbdc83a2dd3e4bd11524ae74fc963504f7bf730b54
+size 4998658670

model-00018-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7e8e5e2252b00ccfca43b2406a88237e4ad0f0b58b1990076fc1926c1066bb8
+size 4999044638

model-00019-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100f37312e61b8d02629386544f8ae1544beb2a1206e8d58ed08df0050fd743d
+size 4998658613

model-00020-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4a6f6ee5dc66c52af55d1ce7d2947dbfaefa382954d3abfadc07568ba1f672
+size 4999044422

model-00021-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb1cafd1d8bac2ffe8b29998e8504d3dcf2025eecff10c54b90ab55871c27ac
+size 4996319067

model-00022-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b41963defe627efba36062d07791730e9f027ce620b220122a3c8a3596fcf9bb
+size 4979744240

model-00023-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc909b808e1c944be33822b5b364d05f06e910158c38d247f8db253e6b7a8f64
+size 4999044392

model-00024-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1731b723bc23918f4ba85cc992afc9588ababa5d5c95810bc19253e777f9633c
+size 4998658602

model-00025-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c68fdc1aaa291921b14dab0cc0cda02a1dc22b98d7e0ce9b09b5bc16364fed4
+size 4999044794

model-00026-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cd7d20331c37c059a2d3ce4bc42c120e9b902036b9d1450a37c8d44cef2434e
+size 4998658469

model-00027-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1778fa8485c9bb1854935139921d984c0a73008738be87c7b71125090e9094e4
+size 4999044033

model-00028-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e4f7962fecf648ee4abbe901f7fada853e407b716eccfe3bec5f9884816644a
+size 4999043968

model-00029-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f19c9f2e70ed7b8836dcfbb65ce56b4c3cc24be1ad561a8e71134e067b6d0290
+size 4998658664

model-00030-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db00eb3a75534e473a6e168f7c23fdb0dbf8db36931878dc2b5d407388f966f
+size 4999044626

model-00031-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:034d767cdd37e40f49dc5019558dd1a3d04a22d8dd37d4c9da8f4099a1e1d65c
+size 4998658592

model-00032-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fc9a26a3cb425777abc0ff789c49ec5699b9dbb8a2298b4c7e67b4e8ef08d4
+size 4999044464

model-00033-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8dbea0c3ecaa21ffdf5127d9c368de4b43bd39a85b3ad7582fa474ff2a8b128
+size 4999019807

model-00034-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0080540f863dc4c831cbaf95a2ce8939d19cff2853a60e6e358aa482c9cd4242
+size 4998682670

model-00035-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e01b6ac5932bf3b7e7944ec9a97bfd8e184f6373264cac27e84ed86808945e7a
+size 4999044358

model-00036-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca588e9745123f6c68eec89a24b18d6bcdf0dda08ec186a02d03804a5f1d56b5
+size 4998658606

model-00037-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47a93bd3f9c82c5a8b400a5f7239de9074a2964ffbd4fb3a28fffca20874541c
+size 4999044816

model-00038-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0242a73372482b179c216d157e07116290e4c5c127639177e2c7cc99a1a9cd7e
+size 4998658462

model-00039-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e51a7107fcb97dbcd8af7914d04093ad2e937bb0b13dac02f9ca74596c685c3
+size 4999044046

model-00040-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616d10f389fe63716ba76779bc8341777e25b81e9baf385e920133ca968787d8
+size 4999043966

model-00041-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d598534eb86640f7abcba394c19d97fdab18df13781ca24a27c128d38be6d16
+size 4998658660

model-00042-of-00042.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13a9241e0658adfd259210b6f9d21769b92554d87757514e46b8dea093cb25cb
+size 4925719795

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"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}