Upload folder using huggingface_hub (#1)

- a0841a2f082daaf44c629982dd9b4a521113c3c6315955e4a918f8d1520becd6 (59757c069e170876812bad033a2635ebca42a570)

README.md

@@ -0,0 +1,36 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- mlx
+datasets:
+- Skylion007/openwebtext
+- JeanKaddour/minipile
+pipeline_tag: text-generation
+inference:
+  parameters:
+    do_sample: true
+    temperature: 0.5
+    top_p: 0.5
+    top_k: 50
+    max_new_tokens: 250
+    repetition_penalty: 1.176
+---
+
+# mlx-community/TinyMistral-248M-4bits
+
+The Model [mlx-community/TinyMistral-248M-4bits](https://huggingface.co/mlx-community/TinyMistral-248M-4bits) was converted to MLX format from [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M) using mlx-lm version **0.14.0**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/TinyMistral-248M-4bits")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,28 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 12,
+    "num_key_value_heads": 8,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "sliding_window": 32,
+    "tie_word_embeddings": false,
+    "torch_dtype": "float16",
+    "transformers_version": "4.35.0",
+    "use_cache": true,
+    "vocab_size": 32005
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbf81f6590a0972a76ea341991774a13c1d4f7bc357fa6d3e6b513c2f1d2131
+size 139581092

model.safetensors.index.json

@@ -0,0 +1,290 @@
+{
+    "metadata": {
+        "total_size": 139550336
+    },
+    "weight_map": {
+        "lm_head.biases": "model.safetensors",
+        "lm_head.scales": "model.safetensors",
+        "lm_head.weight": "model.safetensors",
+        "model.embed_tokens.biases": "model.safetensors",
+        "model.embed_tokens.scales": "model.safetensors",
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>"
+  ],
+  "bos_token": {
+    "content": "<|bos|>",
+    "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,88 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<|bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|ASSISTANT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|USER|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>"
+  ],
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "max_length": 1536,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}