Add files using upload-large-folder tool

README.md

@@ -0,0 +1,153 @@
+---
+license: apache-2.0
+datasets:
+- bigcode/the-stack
+- bigcode/the-stack-v2
+- bigcode/starcoderdata
+- bigcode/commitpack
+library_name: mlx
+tags:
+- code
+- mlx
+base_model: JetBrains/Mellum-4b-base
+pipeline_tag: text-generation
+model-index:
+- name: Mellum-4b-base
+  results:
+  - task:
+      type: text-generation
+    dataset:
+      name: RepoBench 1.1 (Python)
+      type: tianyang/repobench_python_v1.1
+    metrics:
+    - type: exact_match
+      value: 0.2591
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.2797
+      name: EM ≤ 8k
+      verified: false
+    - type: exact_match
+      value: 0.282
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.2795
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.2777
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.2453
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.211
+      name: EM
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: RepoBench 1.1 (Java)
+      type: tianyang/repobench_java_v1.1
+    metrics:
+    - type: exact_match
+      value: 0.2858
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.3108
+      name: EM ≤ 8k
+      verified: false
+    - type: exact_match
+      value: 0.3202
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.3212
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.291
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.2492
+      name: EM
+      verified: false
+    - type: exact_match
+      value: 0.2474
+      name: EM
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: SAFIM
+      type: gonglinyuan/safim
+    metrics:
+    - type: pass@1
+      value: 0.3811
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 0.253
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 0.3839
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 0.5065
+      name: pass@1
+      verified: false
+  - task:
+      type: text-generation
+    dataset:
+      name: HumanEval Infilling (Single-Line)
+      type: loubnabnl/humaneval_infilling
+    metrics:
+    - type: pass@1
+      value: 0.6621
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 0.3852
+      name: pass@1
+      verified: false
+    - type: pass@1
+      value: 0.2969
+      name: pass@1
+      verified: false
+---
+
+# mlx-community/Mellum-4b-base
+
+This model [mlx-community/Mellum-4b-base](https://huggingface.co/mlx-community/Mellum-4b-base) was
+converted to MLX format from [JetBrains/Mellum-4b-base](https://huggingface.co/JetBrains/Mellum-4b-base)
+using mlx-lm version **0.25.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Mellum-4b-base")
+
+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)
+```

config.json

@@ -0,0 +1,31 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 0,
+    "eos_token_id": 0,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 8256,
+    "max_position_embeddings": 8192,
+    "max_sequence_length": 8192,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 24,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 24,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.51.3",
+    "use_cache": true,
+    "vocab_size": 98304
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3a879238ccf81787c1723fe9b02756cb8e0d17b54597512cbaf6680b3fff6e
+size 5334635649

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45d232b50f26c072f353b9c3ebe730a4f75e86768b05a61db87eb4fd7226180
+size 2703892203

model.safetensors.index.json

@@ -0,0 +1,281 @@
+{
+    "metadata": {
+        "total_size": 8038496256,
+        "total_parameters": 4019248128
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00002-of-00002.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+        "model.norm.weight": "model-00002-of-00002.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,58 @@
+{
+  "additional_special_tokens": [
+    "<gh_stars>",
+    "</system>",
+    "<issue_start>",
+    "</think>",
+    "<commit_after>",
+    "<assistant>",
+    "<jupyter_text>",
+    "<fim_middle>",
+    "</assistant>",
+    "<jupyter_code>",
+    "<user>",
+    "<filename>",
+    "<think>",
+    "<fim_suffix>",
+    "<fim_prefix>",
+    "<commit_msg>",
+    "<fim_pad>",
+    "<system>",
+    "<issue_comment>",
+    "<reponame>",
+    "<jupyter_start>",
+    "<issue_closed>",
+    "<commit_before>",
+    "<empty_output>",
+    "<jupyter_output>",
+    "</user>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,259 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "19": {
+      "content": "<system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "20": {
+      "content": "</system>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "21": {
+      "content": "<user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "22": {
+      "content": "</user>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "23": {
+      "content": "<assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "24": {
+      "content": "</assistant>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "25": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "26": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<gh_stars>",
+    "</system>",
+    "<issue_start>",
+    "</think>",
+    "<commit_after>",
+    "<assistant>",
+    "<jupyter_text>",
+    "<fim_middle>",
+    "</assistant>",
+    "<jupyter_code>",
+    "<user>",
+    "<filename>",
+    "<think>",
+    "<fim_suffix>",
+    "<fim_prefix>",
+    "<commit_msg>",
+    "<fim_pad>",
+    "<system>",
+    "<issue_comment>",
+    "<reponame>",
+    "<jupyter_start>",
+    "<issue_closed>",
+    "<commit_before>",
+    "<empty_output>",
+    "<jupyter_output>",
+    "</user>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}