Add files using upload-large-folder tool

README.md

@@ -0,0 +1,40 @@
+---
+license: apache-2.0
+base_model: allenai/Olmo-3.1-32B-Think
+language:
+- en
+datasets:
+- allenai/Dolci-Think-RL
+library_name: mlx
+pipeline_tag: text-generation
+tags:
+- mlx
+---
+
+# mlx-community/Olmo-3.1-32B-Think-4bit
+
+This model [mlx-community/Olmo-3.1-32B-Think-4bit](https://huggingface.co/mlx-community/Olmo-3.1-32B-Think-4bit) was
+converted to MLX format from [allenai/Olmo-3.1-32B-Think](https://huggingface.co/allenai/Olmo-3.1-32B-Think)
+using mlx-lm version **0.29.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Olmo-3.1-32B-Think-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, return_dict=False,
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```

chat_template.jinja

@@ -0,0 +1,16 @@
+{% set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 %}{% if not has_system %}{{ '<|im_start|>system
+You are Olmo, a helpful AI assistant built by Ai2. Your date cutoff is December 2024, and your model weights are available at https://huggingface.co/allenai.<|im_end|>
+' }}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system
+' + message['content'] }}{% if message.get('functions', none) is not none %}{{ ' <functions>' + message['functions'] + '</functions><|im_end|>
+' }}{% else %}{{ ' You do not currently have access to any functions. <functions></functions><|im_end|>
+' }}{% endif %}{% elif message['role'] == 'user' %}{% if message.get('functions', none) is not none %}{{ '<|im_start|>user
+' + message['content'] + '
+' + '<functions>' + message['functions'] + '</functions><|im_end|>
+' }}{% else %}{{ '<|im_start|>user
+' + message['content'] + '<|im_end|>
+' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant
+' }}{% if message.get('content', none) is not none %}{{ message['content'] }}{% endif %}{% if message.get('function_calls', none) is not none %}{{ '<function_calls>' + message['function_calls'] + '</function_calls>' }}{% endif %}{% if not loop.last %}{{ '<|im_end|>' + '
+' }}{% else %}{{ eos_token }}{% endif %}{% elif message['role'] == 'environment' %}{{ '<|im_start|>environment
+' + message['content'] + '<|im_end|>
+' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|im_start|>assistant
+<think>' }}{% endif %}{% endfor %}

config.json

@@ -0,0 +1,110 @@
+{
+    "architectures": [
+        "Olmo3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "eos_token_id": 100257,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 27648,
+    "layer_types": [
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "sliding_attention",
+        "full_attention"
+    ],
+    "max_position_embeddings": 65536,
+    "model_type": "olmo3",
+    "num_attention_heads": 40,
+    "num_hidden_layers": 64,
+    "num_key_value_heads": 8,
+    "pad_token_id": 100277,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "attention_factor": 1.2079441541679836,
+        "beta_fast": 32.0,
+        "beta_slow": 1.0,
+        "factor": 8.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "yarn"
+    },
+    "rope_theta": 500000,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.1",
+    "use_cache": false,
+    "vocab_size": 100278
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": 100257,
+  "pad_token_id": 100277,
+  "transformers_version": "4.57.1",
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "max_new_tokens": 32768
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9729ae2a4a6273a377634393d7158872ade05626d3adeebb02af75573a0d5f99
+size 5341298988

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf58beb4943e806a26b371e213973c359b36b005564450fcf81ec622a4b01b9
+size 5366601614

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8140e30c97635b3dc9accde3250443300ca349faaa573d8285cbe5b36addccea
+size 5331246640

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86ab304df9046448328b146d1865f9035794b039f2bcc708c0079e744fa92d3
+size 2093907822

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 65536,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}