Add files using upload-large-folder tool

README.md

@@ -0,0 +1,35 @@
+---
+base_model: TheDrummer/Behemoth-R1-123B-v2
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+- mlx
+---
+
+# beezu/Behemoth-R1-123B-v2-MLX-MXFP4
+
+This model [beezu/Behemoth-R1-123B-v2-MLX-MXFP4](https://huggingface.co/beezu/Behemoth-R1-123B-v2-MLX-MXFP4) was
+converted to MLX format from [TheDrummer/Behemoth-R1-123B-v2](https://huggingface.co/TheDrummer/Behemoth-R1-123B-v2)
+using mlx-lm version **0.28.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("beezu/Behemoth-R1-123B-v2-MLX-MXFP4")
+
+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 @@
+{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + '[/INST]' }}{% elif message['role'] == 'system' %}{{ '[SYSTEM_PROMPT] ' + message['content'] + '[/SYSTEM_PROMPT]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + message['content'] + eos_token }}{% else %}{{ raise_exception('Only user, system and assistant roles are supported!') }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,36 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 12288,
+    "initializer_range": 0.02,
+    "intermediate_size": 28672,
+    "max_position_embeddings": 131072,
+    "model_type": "mistral",
+    "num_attention_heads": 96,
+    "num_hidden_layers": 88,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "mxfp4"
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "mxfp4"
+    },
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.55.2",
+    "use_cache": true,
+    "vocab_size": 32768
+}

model-00001-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ebbf6aa5ce27efdd81231f84e067795b28968cb9d7963e25de6520729657b1e
+size 5361464013

model-00002-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7565382a2999b52d9982e268607045d1e419b1f381b68ced751c6f6b590d84f
+size 5321356775

model-00003-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bdea4271705cb9234a2c27b12c4b73fbb53f4873fa915b6c79a9d85922b98c5
+size 5334725441

model-00004-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c1894eead71916c361bad394dd391d0321fb40ddea9993caae56c1ba62ae44
+size 5334725473

model-00005-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab3fddfd586a1befc2ac79c3dd3da6b432df31d62c73d5d3fd2faae8937704a
+size 5334774832

model-00006-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db6d8e456d9d97a4d917a86b40579c2e17ae5e798260d9f6457de5d21669227
+size 5321356801

model-00007-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a448eb22b1e9c7a88216468c351246c907a48445e74661251a53bb0f0ea58a56
+size 5334725461

model-00008-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2042034bcb5b096ecf93fe4d6576152fd2b7587d83ddbe3b7d449bf4e7537e2
+size 5334725479

model-00009-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43e4203f648b809f51a3f38b9925585378f214119db549ae1612b8eb2383db0f
+size 5334774850

model-00010-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9640b2be73ebfd2495522fc9362ba72cfa88c34dacd36e98f7a92e79320f05bd
+size 5321356805

model-00011-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d65aa494450ef153fd6624047d508f92c34fe33382a2e9ce4096cffc7b8ef0
+size 5334725469

model-00012-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44bd17a624ba0eeae8302a3dbc888f38e21189d980a1dc356b57400b8d900eb1
+size 5334725467

model-00013-of-00013.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de05d97a2d400548d4c095141a669b18983a2b32c9f083501fbbac198798613e
+size 1136519690

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b968b8dc352f42192367337c78ccc61e1eaddc6d641a579372d4f20694beb7a
+size 587562