初始化项目，由ModelHub XC社区提供模型

Model: zed-industries/zeta-2.1
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+base_model: ByteDance-Seed/Seed-Coder-8B-Base
+tags:
+- text-generation-inference
+- transformers
+- edit-prediction
+- next-edit-suggestion
+license: apache-2.0
+language:
+- en
+---
+
+# Zeta 2.1
+
+Zeta 2.1 is a code edit prediction (also known as next-edit suggestion) model finetuned from `ByteDance-Seed/Seed-Coder-8B-Base`.  
+
+Given code context, edits history and an editable region around the cursor, it predicts the rewritten content for that region.
+
+- **Developed by:** Zed Industries  
+- **License:** Apache-2.0  
+- **Fine-tuned from:** ByteDance-Seed/Seed-Coder-8B-Base  
+- **Model version:** 0323-multi-region-filtered-r3
+
+## Prompt format
+
+The model uses a SPM (suffix-prefix-middle) style prompt with numbered multi-region markers for editable regions:
+
+
+Here is a minimal example:
+
+```
+<[fim-suffix]>
+code after editable region
+<[fim-prefix]><filename>related/file.py
+related file content
+
+<filename>edit_history
+--- a/some_file.py
++++ b/some_file.py
+-old
++new
+
+<filename>path/to/target_file.py
+code before editable region
+<|marker_1|>
+code that
+needs to<|user_cursor|>
+be rewritten
+<|marker_2|>
+<[fim-middle]>
+```
+
+Expected output (should be generated by the model, without backticks):
+
+```
+<|marker_1|>
+revised content for
+the editable region
+<|marker_2|>
+```
+
+Here is a real-world example:
+- [Sample prompt input](./sample.prompt)
+- [Sample model output](./sample.output)

config.json

@@ -0,0 +1,33 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.1,
+    "bos_token_id": 0,
+    "torch_dtype": "bfloat16",
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.009882118,
+    "intermediate_size": 14336,
+    "layer_norm_eps": null,
+    "max_position_embeddings": 32768,
+    "mlp_bias": false,
+    "model_type": "llama",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 8,
+    "pad_token_id": 1,
+    "pretraining_tp": 1,
+    "resid_pdrop": 0.1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "rope_theta": 500000.0,
+    "tie_word_embeddings": false,
+    "transformers_version": "4.57.3",
+    "unsloth_version": "2026.1.3",
+    "use_cache": true,
+    "vocab_size": 155136
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb82df7d66542e2b329a3f8029c561168afcc235082740c4290fe95685b266f8
+size 4962001760

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ad1dd0e3b8f3420225de60779befabada9385aac83c54503d5e67d9b9efe96
+size 4915916160

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84549de401f30b1684c1504be9e9ec4f205f14c6bf724b24073c33737dc282fe
+size 4999819336

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93dd7e354018fd22cd8573bc857aa16fdc520d3db1715b900523a25ada3af4e0
+size 1623221024

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16500924416
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

sample.output

@@ -0,0 +1,17 @@
+<|marker_1|>                    return;
+                };
+                let path = project.read(cx).path_for_entry(*active_entry_id, cx);
+                if let Some(path) = path {
+                    if let Some(ix) = project_state
+                        .recent_paths
+                        .iter()
+                        .position(|probe| probe == &path)
+                    {
+                        project_state.recent_paths.remove(ix);
+                    }
+                    project_state.recent_paths.push_front(path);
+                }
+            }
+            project::Event::DiskBasedDiagnosticsFinished<|user_cursor|> { .. } => {
+                if cx.has_flag::<EditPredictionJumpsFeatureFlag>() {
+<|marker_2|>

sample.prompt

@@ -0,0 +1,368 @@
+<[fim-suffix]>
+<[fim-prefix]><filename>zed/crates/project/src/project.rs
+pub struct Project {
+    active_entry: Option<ProjectEntryId>,
+    buffer_ordered_messages_tx: mpsc::UnboundedSender<BufferOrderedMessage>,
+    languages: Arc<LanguageRegistry>,
+    dap_store: Entity<DapStore>,
+    agent_server_store: Entity<AgentServerStore>,
+
+    breakpoint_store: Entity<BreakpointStore>,
+    collab_client: Arc<client::Client>,
+    join_project_response_message_id: u32,
+    task_store: Entity<TaskStore>,
+    user_store: Entity<UserStore>,
+    fs: Arc<dyn Fs>,
+    remote_client: Option<Entity<RemoteClient>>,
+    // todo lw explain the client_state x remote_client matrix, its super confusing
+    client_state: ProjectClientState,
+    git_store: Entity<GitStore>,
+    collaborators: HashMap<proto::PeerId, Collaborator>,
+    client_subscriptions: Vec<client::Subscription>,
+    worktree_store: Entity<WorktreeStore>,
+    buffer_store: Entity<BufferStore>,
+    context_server_store: Entity<ContextServerStore>,
+    image_store: Entity<ImageStore>,
+    lsp_store: Entity<LspStore>,
+    _subscriptions: Vec<gpui::Subscription>,
+    buffers_needing_diff: HashSet<WeakEntity<Buffer>>,
+    git_diff_debouncer: DebouncedDelay<Self>,
+    remotely_created_models: Arc<Mutex<RemotelyCreatedModels>>,
+    terminals: Terminals,
+    node: Option<NodeRuntime>,
+    search_history: SearchHistory,
+    search_included_history: SearchHistory,
+    search_excluded_history: SearchHistory,
+    snippets: Entity<SnippetProvider>,
+    environment: Entity<ProjectEnvironment>,
+    settings_observer: Entity<SettingsObserver>,
+    toolchain_store: Option<Entity<ToolchainStore>>,
+    agent_location: Option<AgentLocation>,
+    downloading_files: Arc<Mutex<HashMap<(WorktreeId, String), DownloadingFile>>>,
+}
+...
+pub enum Event {
+    LanguageServerAdded(LanguageServerId, LanguageServerName, Option<WorktreeId>),
+    LanguageServerRemoved(LanguageServerId),
+    LanguageServerLog(LanguageServerId, LanguageServerLogType, String),
+...
+    LanguageServerBufferRegistered {
+        server_id: LanguageServerId,
+...
+    },
+    ToggleLspLogs {
+        server_id: LanguageServerId,
+...
+    },
+    Toast {
+        notification_id: SharedString,
+...
+    },
+    HideToast {
+        notification_id: SharedString,
+    },
+    LanguageServerPrompt(LanguageServerPromptRequest),
+    LanguageNotFound(Entity<Buffer>),
+    ActiveEntryChanged(Option<ProjectEntryId>),
+    ActivateProjectPanel,
+    WorktreeAdded(WorktreeId),
+    WorktreeOrderChanged,
+    WorktreeRemoved(WorktreeId),
+    WorktreeUpdatedEntries(WorktreeId, UpdatedEntriesSet),
+    DiskBasedDiagnosticsStarted {
+        language_server_id: LanguageServerId,
+    },
+    DiskBasedDiagnosticsFinished {
+        language_server_id: LanguageServerId,
+    },
+    DiagnosticsUpdated {
+        paths: Vec<ProjectPath>,
+...
+    },
+    RemoteIdChanged(Option<u64>),
+    DisconnectedFromHost,
+    DisconnectedFromRemote {
+        server_not_running: bool,
+    },
+    Closed,
+    DeletedEntry(WorktreeId, ProjectEntryId),
+    CollaboratorUpdated {
+        old_peer_id: proto::PeerId,
+...
+    },
+    CollaboratorJoined(proto::PeerId),
+    CollaboratorLeft(proto::PeerId),
+    HostReshared,
+    Reshared,
+    Rejoined,
+    RefreshInlayHints {
+        server_id: LanguageServerId,
+...
+    },
+    RefreshSemanticTokens {
+        server_id: LanguageServerId,
+...
+    },
+    RefreshCodeLens,
+    RevealInProjectPanel(ProjectEntryId),
+    SnippetEdit(BufferId, Vec<(lsp::Range, Snippet)>),
+    ExpandedAllForEntry(WorktreeId, ProjectEntryId),
+    EntryRenamed(ProjectTransaction, ProjectPath, PathBuf),
+    WorkspaceEditApplied(ProjectTransaction),
+    AgentLocationChanged,
+    BufferEdited,
+}
+...
+pub struct ProjectPath {
+    pub worktree_id: WorktreeId,
+    pub path: Arc<RelPath>,
+}
+...
+<filename>zed/crates/edit_prediction/src/edit_prediction.rs
+pub struct EditPredictionJumpsFeatureFlag;
+...
+pub struct EditPredictionStore {
+    client: Arc<Client>,
+    user_store: Entity<UserStore>,
+    llm_token: LlmApiToken,
+    _llm_token_subscription: Subscription,
+    projects: HashMap<EntityId, ProjectState>,
+    update_required: bool,
+    edit_prediction_model: EditPredictionModel,
+    zeta2_raw_config: Option<Zeta2RawConfig>,
+    pub sweep_ai: SweepAi,
+    pub mercury: Mercury,
+    data_collection_choice: DataCollectionChoice,
+    reject_predictions_tx: mpsc::UnboundedSender<EditPredictionRejection>,
+    shown_predictions: VecDeque<EditPrediction>,
+    rated_predictions: HashSet<EditPredictionId>,
+}
+...
+struct ProjectState {
+    events: VecDeque<StoredEvent>,
+    last_event: Option<LastEvent>,
+    recent_paths: VecDeque<ProjectPath>,
+    registered_buffers: HashMap<gpui::EntityId, RegisteredBuffer>,
+    current_prediction: Option<CurrentEditPrediction>,
+    next_pending_prediction_id: usize,
+    pending_predictions: ArrayVec<PendingPrediction, 2>,
+    debug_tx: Option<mpsc::UnboundedSender<DebugEvent>>,
+    last_edit_prediction_refresh: Option<(EntityId, Instant)>,
+    last_jump_prediction_refresh: Option<(EntityId, Instant)>,
+    cancelled_predictions: HashSet<usize>,
+    context: Entity<RelatedExcerptStore>,
+    license_detection_watchers: HashMap<WorktreeId, Rc<LicenseDetectionWatcher>>,
+    user_actions: VecDeque<UserActionRecord>,
+    _subscriptions: [gpui::Subscription; 2],
+    copilot: Option<Entity<Copilot>>,
+}
+...
+impl EditPredictionStore {
+    pub fn try_global(cx: &App) -> Option<Entity<Self>> {
+...
+    }
+
+    pub fn global(
+        client: &Arc<Client>,
+        user_store: &Entity<UserStore>,
+        cx: &mut App,
+    ) -> Entity<Self> {
+...
+    }
+
+    pub fn new(client: Arc<Client>, user_store: Entity<UserStore>, cx: &mut Context<Self>) -> Self {
+...
+    }
+
+    fn zeta2_raw_config_from_env() -> Option<Zeta2RawConfig> {
+...
+    }
+
+    pub fn set_edit_prediction_model(&mut self, model: EditPredictionModel) {
+        self.edit_prediction_model = model;
+    }
+
+    pub fn set_zeta2_raw_config(&mut self, config: Zeta2RawConfig) {
+        self.zeta2_raw_config = Some(config);
+    }
+
+    pub fn zeta2_raw_config(&self) -> Option<&Zeta2RawConfig> {
+        self.zeta2_raw_config.as_ref()
+    }
+
+    pub fn icons(&self, cx: &App) -> edit_prediction_types::EditPredictionIconSet {
+...
+    }
+
+    pub fn has_sweep_api_token(&self, cx: &App) -> bool {
+        self.sweep_ai.api_token.read(cx).has_key()
+    }
+
+    pub fn has_mercury_api_token(&self, cx: &App) -> bool {
+        self.mercury.api_token.read(cx).has_key()
+    }
+
+    pub fn clear_history(&mut self) {
+...
+    }
+
+    pub fn clear_history_for_project(&mut self, project: &Entity<Project>) {
+...
+    }
+
+    pub fn edit_history_for_project(
+        &self,
+        project: &Entity<Project>,
+        cx: &App,
+    ) -> Vec<StoredEvent> {
+...
+    }
+
+    pub fn context_for_project<'a>(
+        &'a self,
+        project: &Entity<Project>,
+        cx: &'a mut App,
+    ) -> Vec<RelatedFile> {
+...
+    }
+
+    pub fn copilot_for_project(&self, project: &Entity<Project>) -> Option<Entity<Copilot>> {
+...
+    }
+
+    pub fn start_copilot_for_project(
+        &mut self,
+        project: &Entity<Project>,
+        cx: &mut Context<Self>,
+    ) -> Option<Entity<Copilot>> {
+...
+    }
+
+    pub fn context_for_project_with_buffers<'a>(
+        &'a self,
+        project: &Entity<Project>,
+        cx: &'a mut App,
+    ) -> Vec<(RelatedFile, Entity<Buffer>)> {
+...
+    }
+
+    fn handle_project_event(
+        &mut self,
+        project: Entity<Project>,
+        event: &project::Event,
+        cx: &mut Context<Self>,
+    ) {
+...
+                let Some(project_state) = self.projects.get_mut(&project.entity_id()) else {
+...
+                if let Some(path) = path {
+...
+    }
+
+    fn register_buffer_impl<'a>(
+        project_state: &'a mut ProjectState,
+        buffer: &Entity<Buffer>,
+        project: &Entity<Project>,
+        cx: &mut Context<Self>,
+    ) -> &'a mut RegisteredBuffer {
+...
+    }
+
+    pub fn refresh_prediction_from_diagnostics(
+        &mut self,
+        project: Entity<Project>,
+        scope: DiagnosticSearchScope,
+        cx: &mut Context<Self>,
+    ) {
+...
+    }
+
+    fn predictions_enabled_at(
+        snapshot: &BufferSnapshot,
+        position: Option<language::Anchor>,
+        cx: &App,
+    ) -> bool {
+...
+<filename>zed/crates/gpui/src/app/context.rs
+pub struct Context<'a, T> {
+    app: &'a mut App,
+    entity_state: WeakEntity<T>,
+}
+...
+<filename>zed/crates/feature_flags/src/feature_flags.rs
+impl FeatureFlagAppExt for App {
+...
+    fn has_flag<T: FeatureFlag>(&self) -> bool {
+        self.try_global::<FeatureFlags>()
+            .map(|flags| flags.has_flag::<T>())
+            .unwrap_or_else(|| {
+                (cfg!(debug_assertions) && T::enabled_for_staff() && !*ZED_DISABLE_STAFF)
+                    || T::enabled_for_all()
+            })
+    }
+...
+}
+...
+<filename>zed/crates/gpui/src/app/entity_map.rs
+pub struct Entity<T> {
+    #[deref]
+    #[deref_mut]
+    pub(crate) any_entity: AnyEntity,
+    pub(crate) entity_type: PhantomData<fn(T) -> T>,
+}
+...
+
+<filename>edit_history
+--- a/zed/crates/edit_prediction/src/edit_prediction.rs
++++ b/zed/crates/edit_prediction/src/edit_prediction.rs
+@@ -1035,7 +1035,7 @@
+                     project_state.recent_paths.push_front(path);
+                 }
+             }
+-            project::Event::DiagnosticsUpdated { .. } => {
++            project::Event::Disk { .. } => {
+                 if cx.has_flag::<EditPredictionJumpsFeatureFlag>() {
+                     self.refresh_prediction_from_diagnostics(
+                         project,
+
+<filename>crates/edit_prediction/src/edit_prediction.rs
+    ) {
+        if !is_ep_store_provider(all_language_settings(None, cx).edit_predictions.provider) {
+            return;
+        }
+        // TODO [zeta2] init with recent paths
+        match event {
+            project::Event::ActiveEntryChanged(Some(active_entry_id)) => {
+                let Some(project_state) = self.projects.get_mut(&project.entity_id()) else {
+<|marker_1|>                    return;
+                };
+                let path = project.read(cx).path_for_entry(*active_entry_id, cx);
+                if let Some(path) = path {
+                    if let Some(ix) = project_state
+                        .recent_paths
+                        .iter()
+                        .position(|probe| probe == &path)
+                    {
+                        project_state.recent_paths.remove(ix);
+                    }
+                    project_state.recent_paths.push_front(path);
+                }
+            }
+            project::Event::Disk<|user_cursor|> { .. } => {
+                if cx.has_flag::<EditPredictionJumpsFeatureFlag>() {
+<|marker_2|>                    self.refresh_prediction_from_diagnostics(
+                        project,
+                        DiagnosticSearchScope::Global,
+                        cx,
+                    );
+                }
+            }
+            _ => (),
+        }
+    }
+
+    fn register_buffer_impl<'a>(
+        project_state: &'a mut ProjectState,
+        buffer: &Entity<Buffer>,
+        project: &Entity<Project>,<|marker_3|>
+<[fim-middle]>

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<[begin▁of▁sentence]>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<[end▁of▁sentence]>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<[PAD▁TOKEN]>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<[SEP▁TOKEN]>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6520146c388c495a98bbea62ff6d00c0a8935bed33622e33bb33ec71aaafed
+size 11891696