Add files using upload-large-folder tool

README.md

@@ -0,0 +1,40 @@
+---
+license: apache-2.0
+base_model: allenai/Olmo-3-7B-RLZero-Mix
+language:
+- en
+datasets:
+- allenai/Dolci-RLZero-Mix-7B
+library_name: mlx
+tags:
+- mlx
+pipeline_tag: text-generation
+---
+
+# mlx-community/Olmo-3-7B-RLZero-Mix-bfloat16
+
+This model [mlx-community/Olmo-3-7B-RLZero-Mix-bfloat16](https://huggingface.co/mlx-community/Olmo-3-7B-RLZero-Mix-bfloat16) was
+converted to MLX format from [allenai/Olmo-3-7B-RLZero-Mix](https://huggingface.co/allenai/Olmo-3-7B-RLZero-Mix)
+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("mlx-community/Olmo-3-7B-RLZero-Mix-bfloat16")
+
+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 +1,16 @@
+{% set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 %}{% if not has_system %}{{ '<|im_start|>system
+You are OLMo, a helpful function-calling AI assistant built by Ai2. Your date cutoff is November 2024, and your model weights are available at https://huggingface.co/allenai. You do not currently have access to any functions. <functions></functions><|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 +1,68 @@
+{
+    "architectures": [
+        "Olmo3ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "eos_token_id": 100257,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "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"
+    ],
+    "max_position_embeddings": 65536,
+    "model_type": "olmo3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 32,
+    "pad_token_id": 100277,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "attention_factor": 1.2079441541679836,
+        "beta_fast": 32,
+        "beta_slow": 1,
+        "factor": 8.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "yarn"
+    },
+    "rope_theta": 500000,
+    "sliding_window": 4096,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.0",
+    "use_cache": true,
+    "vocab_size": 100278
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.54.0.dev0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e3ccd1ba74b302aa8aae45d8b31c3e8ac12e42f74da4f839dae764a839372d7
+size 5341214752

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c3faf3505f960c50296aad8bf3471a6cc8dfe20c237a588555ba48bd82cd2f
+size 5329322782

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded589c3401bebd7385fd75041ff10166f49cdf07caad29e226006af05fd4824
+size 3925526100

model.safetensors.index.json

@@ -0,0 +1,363 @@
+{
+    "metadata": {
+        "total_size": 14596022272,
+        "total_parameters": 7298011136
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00003-of-00003.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+        "model.norm.weight": "model-00003-of-00003.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "|||PHONE_NUMBER|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100262": {
+      "content": "|||EMAIL_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100263": {
+      "content": "|||IP_ADDRESS|||",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100267": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100268": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100269": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100270": {
+      "content": "<functions>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100271": {
+      "content": "</functions>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100272": {
+      "content": "<function_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100273": {
+      "content": "</function_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100274": {
+      "content": "<answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100275": {
+      "content": "</answer>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}