Add files using upload-large-folder tool

.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

README.md

@@ -0,0 +1,64 @@
+---
+language:
+- en
+license: llama3
+tags:
+- Llama-3.1
+- instruct
+- finetune
+- reasoning
+- hybrid-mode
+- chatml
+- function calling
+- tool use
+- json mode
+- structured outputs
+- atropos
+- dataforge
+- long context
+- roleplaying
+- chat
+- mlx
+base_model: NousResearch/Hermes-4-405B
+library_name: mlx
+widget:
+- example_title: Hermes 4
+  messages:
+  - role: system
+    content: You are Hermes 4, a capable, neutrally-aligned assistant. Prefer concise,
+      correct answers.
+  - role: user
+    content: Explain the difference between BFS and DFS to a new CS student.
+pipeline_tag: text-generation
+model-index:
+- name: Hermes-4-Llama-3.1-405B
+  results: []
+---
+
+# mlx-community/Hermes-4-405B-4bit
+
+This model [mlx-community/Hermes-4-405B-4bit](https://huggingface.co/mlx-community/Hermes-4-405B-4bit) was
+converted to MLX format from [NousResearch/Hermes-4-405B](https://huggingface.co/NousResearch/Hermes-4-405B)
+using mlx-lm version **0.26.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Hermes-4-405B-4bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,76 @@
+{%- set thinking_prompt = 'You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.' %}
+{%- set standard_prompt = 'You are Hermes, created by Nous Research.' %}
+{%- if not thinking is defined %}{% set thinking = false %}{% endif %}
+{%- if not keep_cots is defined %}{% set keep_cots = false %}{% endif %}
+{%- if thinking %}{%- set system_prompt = thinking_prompt %}{%- else %}{%- set system_prompt = standard_prompt %}{%- endif %}
+{%- if tools %}
+    {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- system_prompt }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou are a function calling AI model. You may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": \"<function-name>\", \"arguments\": <args-json-object>}\n</tool_call><|eot_id|>" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + messages[0]['content'] + '<|eot_id|>' }}
+    {%- else %}
+        {{- bos_token + '<|start_header_id|>system<|end_header_id|>\n\n' + system_prompt + '<|eot_id|>' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n\n' + message.content + '<|eot_id|>' }}
+    {%- elif (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }}
+        {%- if message.content %}
+            {%- set content = message['content'] -%}
+            {%- if thinking %}
+                {%- if not keep_cots %}
+                    {%- set content = '<think> </think>' + content.split('</think>', 1)[1] -%}
+                {%- endif %}
+            {%- endif %}
+            {{- '\n' + content + '<|eot_id|>' }}
+        {%- endif %}
+    {%- elif message.role == "assistant" %}
+        {{- '<|start_header_id|>' + message.role + '<|end_header_id|>\n' }}
+        {%- if message.content %}
+            {%- set content = message['content'] -%}
+            {%- if thinking %}
+                {%- if not keep_cots %}
+                    {%- set content = '<think> </think>' + content.split('</think>', 1)[1] -%}
+                {%- endif %}
+            {%- endif %}
+            {{- '\n' + content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|eot_id|>' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|start_header_id|>user<|end_header_id|>\n' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|eot_id|>' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,43 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 128000,
+    "eos_token_id": 128001,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 16384,
+    "initializer_range": 0.02,
+    "intermediate_size": 53248,
+    "max_position_embeddings": 131072,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 128,
+    "num_hidden_layers": 126,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+        "factor": 8.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.52.4",
+    "use_cache": true,
+    "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f135c6cb84476502662e50d7ba5523283372370b2c075ad9ee075ee14522558
+size 5089139565

model-00002-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb027ec6f513e068a31231cd34ea0d8e79a72c8a0b52186d34d7af5e52da9be5
+size 5362621999

model-00003-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9308c47242e3eb88665bc5b506de3a504adf706fc3a5ac2f28cd561dc94231
+size 5245181580

model-00004-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff14189fe04b01b0dd916080459ecf91a772e4771ae7ed4d505e568f9d895796
+size 5360524409

model-00005-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4058cd8af5e78d6ca9fa63b1b2bfb03744fbdd108c09dc42234ec5ac1d4dce2
+size 5362622060

model-00006-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a3cb57e534578c4123b0961aff9866ec3d3136d34b5948ba4f802f0ae759f20
+size 5245181680

model-00007-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d81d3da876cb5d370f4ed27c40c3c0bb21b2d1e8f78235171d67c7e2b0508d35
+size 5352070668

model-00008-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b01efd9ff80bd34b9b1ca43af3fbb6cd5886a01453b1903b70109c445a649653
+size 5352136421

model-00009-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be7355e00d6d6c870a3b0087e215de061f8a395cfd49793f7c9a9bb7cff21be
+size 4943191779

model-00010-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228dc8aaa56565362ba49e6b08b0ecbdbffd415fc53269953ce81067bb98da6f
+size 5352136407

model-00011-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4e4a797c865f8a73624d14799462b8e47ef7b2ab6b4b62ef23c7c094afeb52
+size 5352136429

model-00012-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8365fd4e26d9bcabf8e4361349dc85dee58261a5b9e2b87db8ad376057a7d767
+size 4943191749

model-00013-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb6f2d2f6bc754cfe0d5b6e1a286161ec72eacea87116498cfe2bb6b6dde7b56
+size 5352136403

model-00014-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dafe0b3737f03b524e217a15609e85972a7aab0f974ece2c1b75542e17b6672
+size 5352136425

model-00015-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76dd5b1e321f3612307a884e48b56a23d4fa6582734332db159a4e95d91c1c71
+size 4943191775

model-00016-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b213ac90434ddfcd734a26bcf439000f9fb3fbb8b96afc4e360d41436ace632c
+size 5362622050

model-00017-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f713e777f759a56d413f3e35d0ce1e44da5d4bdc7f7d2793c0901ef729bf3569
+size 5245181666

model-00018-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6712d95194a68a0ac7266d6d80580d9daf1b6e88a41a8e8d860ff2b581ca4b03
+size 5360524446

model-00019-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aa5b5c065d559196e92f3d72e2bcaa0386e36c130e3579c1785f0bdb8681e0a
+size 5362622066

model-00020-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ccc11b9d0f46d654191e3a4ee747c48e9fb6e908d1416340be178975053ddb
+size 5245181660

model-00021-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf7a9d76a29be67bf138ebaa434771bae43f5b34a578d4516e7a3564b711813
+size 5352070648

model-00022-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38d0b96422a88901ccc4795ec0ac1350354c97a81e3b5347db8d6e110055bac
+size 5352136441

model-00023-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e51b91eaee2c5f3639f98caeabef2fdc6ad8b4ed915ccaea8c46083efd8a788
+size 4943191801

model-00024-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7e6a1bc92b3eaf18583fb4c90e61c80b5a20fe7863620f86880ed483b11e6c
+size 5352136421

model-00025-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:846162f856af9efcad5b75efe8544866ebbb6d6a8fe754f0fd27e6ad4c1edfc3
+size 5352136427

model-00026-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c48090fc33b8f8bfbf36a9be07b490e41c500bf67bd021b2141b0370ad4884b
+size 4943191777

model-00027-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11977525eec5492c4b4a0830abba7a9c2c26f584618e2dd936cab89dfc0b71ce
+size 5352136423

model-00028-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13e9646701f1a624dd99433463d7a0fd83b79096a58ae3cd90c402e2a6e661ce
+size 5352136423

model-00029-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e007a2b0c5e9da542dd09ea8a5db88a2521afbfe3b2a358b7de2d87bba24712
+size 4943191787

model-00030-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e05e17b8fb69d6495eb18cfaab1b0c09db405dd7cde3a449c2594a38ece398
+size 5362622066

model-00031-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08260d439fe10772c2533cb22c08bb84fb007b5057eee97431967229b33c965
+size 5245181660

model-00032-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773ded2c7d3a76a813ca770a036012eee9076514d29a8bc93e6e424a085aaf49
+size 5360524448

model-00033-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698994f371807092b0ed05f44e50d98380f5addd2f904d2a933d709f61a506ab
+size 5362622080

model-00034-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e9145a665d80ca79212b45d2aa79d16b4eb6d0ccd5a1ec76d42ab9ede988d4
+size 5245181662

model-00035-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1ad1a3fd10665a79a5e52d145e2c2dff63cc17aa62f64e6fc993e668cb2966
+size 5352070715

model-00037-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1204edbc681b158fc8509441dd31bfeb08f43a3668a4d78595b5b5c3f19059
+size 4943191871

model-00039-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2443164e68e9f33ef04f5f42231f1fc651827b46ef58ffe5e69a90611255db9c
+size 5352136513

model-00040-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce0b98729e653c393e5cc06c9df596b049044724ce88bf8c7818c6b61b4bd2ca
+size 4943191835

model-00041-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b5ad12ffc66f0106946c8e8068306616ebbc7157cd3ba19c48450c01180ef8d
+size 5352136477

model-00042-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55fe48528575b5241f07e002031e9ff2a1a40f45ee141b75e69997118d3711f7
+size 5352136485

model-00043-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a58eed0b222f2bb2e453ae65d709c667c8084827d0ebc42825ae30108a462ff4
+size 4943191845

model-00044-of-00044.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9bf600d4140ec4744a0646497939703da2b85a84df75663b82ba04fa1a45626
+size 2654307981

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": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e4573a56ca97b0233ddc2dd63f634aeee35b84f352d2ce2aaa5992735cfcad
+size 17209827