Upload 16 files

README.md

@@ -0,0 +1,22 @@
+---
+license: apache-2.0
+tags:
+- mlx
+---
+
+# mlx-community/reka-flash-3-mlx-8bit
+
+The Model [mlx-community/reka-flash-3-mlx-8bit](https://huggingface.co/mlx-community/reka-flash-3-mlx-8bit) was converted to MLX format from [RekaAI/reka-flash-3](https://huggingface.co/RekaAI/reka-flash-3) using mlx-lm version **0.18.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/reka-flash-3-mlx-8bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,26 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 100257,
+    "eos_token_id": 100257,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "initializer_range": 0.006,
+    "intermediate_size": 19648,
+    "max_position_embeddings": 32768,
+    "model_type": "llama",
+    "num_attention_heads": 64,
+    "num_hidden_layers": 44,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 8000000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "use_cache": true,
+    "vocab_size": 100352
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a9d519fb3e5124f707ed0fd7e317ea9f579b59e5e11e5eef4f46a0240d40645
+size 5221225171

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00dc53e738f03f81d49de8a671a0512ae3107ab3cae9d152eb248dd6f5c72ef8
+size 5365192767

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2904d3562bf59f14494056ba968ee7582da9a9b230b8ad7f06414f47aecdff
+size 5365192812

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46cada3f07920b27f0f6c34dae5886282f1334f4c9ba64cb81e14bdf9c493d91
+size 5365192810

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f89fce6343ffa16919c8fe822625666f3b95d3912e2fc8c1151bcd1aaf44cf
+size 5365192812

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412ca3741fa4f3ba01d48bcccda55d936a0c3165713c7415b5a9e5ccc459bfef
+size 5365192806

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83ccc338e1350cd0a0896cbdf59391fe0351b612a47877e2b8f5f4016b79382
+size 5365192806

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef399bdd568acf03ecb19cf9ec7ea23fac6f5449b60f69c3a1ffd54dfb19300a
+size 4398628563

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+    "metadata": {
+        "total_size": 41810964480
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00008-of-00008.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+        "model.layers.40.input_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.40.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.40.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.40.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+        "model.layers.41.input_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.41.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.input_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.42.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.input_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+        "model.norm.weight": "model-00008-of-00008.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,46 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|_unuse_missing_100272|>",
+    "<|_unuse_missing_100273|>",
+    "<|_unuse_missing_100274|>",
+    "<|_unuse_missing_100275|>"
+  ],
+  "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
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,203 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|_unuse_missing_100256|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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": "<|_unuse_missing_100261|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|_unuse_missing_100262|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|_unuse_missing_100263|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|_unuse_missing_100264|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|_unuse_missing_100265|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|_unuse_missing_100266|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|_unuse_missing_100267|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|_unuse_missing_100268|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|_unuse_missing_100269|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|_unuse_missing_100270|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|_unuse_missing_100271|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|_unuse_missing_100272|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|_unuse_missing_100273|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|_unuse_missing_100274|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|_unuse_missing_100275|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|fim_suffix|>",
+    "<|endofprompt|>",
+    "<|_unuse_missing_100256|>",
+    "<|_unuse_missing_100261|>",
+    "<|_unuse_missing_100262|>",
+    "<|_unuse_missing_100263|>",
+    "<|_unuse_missing_100264|>",
+    "<|_unuse_missing_100265|>",
+    "<|_unuse_missing_100266|>",
+    "<|_unuse_missing_100267|>",
+    "<|_unuse_missing_100268|>",
+    "<|_unuse_missing_100269|>",
+    "<|_unuse_missing_100270|>",
+    "<|_unuse_missing_100271|>",
+    "<|_unuse_missing_100272|>",
+    "<|_unuse_missing_100273|>",
+    "<|_unuse_missing_100274|>",
+    "<|_unuse_missing_100275|>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set merged_content = messages[0]['content'] + ' ' + messages[1]['content'] %}{% set merged_messages = [{'role': messages[1]['role'], 'content': merged_content}] + messages[2:] %}{% else %}{% set merged_messages = messages %}{% endif %}{% for message in merged_messages %}{{('human' if message['role'] == 'user' else message['role']) + ': ' + (message['content'].split('<reasoning>')|first + message['content'].split('</reasoning>')|last if message['role'] == 'assistant' and '</reasoning>' in message['content'] else message['content'])}}{% if (loop.last and add_generation_prompt and merged_messages[-1]['role'] != 'assistant') or not loop.last %}{{ ' <sep> ' }}{% endif %}{% endfor %}{% if add_generation_prompt and merged_messages[-1]['role'] != 'assistant' %}{{ 'assistant:' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 32768,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}