Upload Devstral SQLCoder SFT model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tekken.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+language:
+- en
+license: other
+base_model:
+- mistralai/Devstral-Small-2505
+tags:
+- text-to-sql
+- sql
+- mistral
+- transformers
+- safetensors
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Devstral SQLCoder SFT
+
+This model is a full-parameter SFT checkpoint for SQL generation, trained from `mistralai/Devstral-Small-2505` and exported to Hugging Face safetensors format.
+
+## Model Details
+
+- Base model: `mistralai/Devstral-Small-2505`
+- Architecture: `MistralForCausalLM`
+- Precision used in training: bf16
+- Max sequence length (training config): 4096
+- Export format: sharded `safetensors` with `model.safetensors.index.json`
+
+## Training Data (Merged)
+
+The SFT run merged the following datasets:
+
+- spider
+- bird
+- bird23-train-filtered
+- synsql-2.5m
+- wikisql
+- gretelai-synthetic
+- sql-create-context
+
+## Intended Use
+
+- Text-to-SQL research and experimentation
+- SQL generation benchmarks and evaluation pipelines
+
+## Limitations
+
+- This model may generate incorrect SQL and should be validated before production use.
+- Performance depends on prompt format, schema context quality, and decoding settings.
+- Evaluate safety and compliance requirements before deployment.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+repo_or_path = "<hf-username-or-org>/<model-repo>"
+
+tokenizer = AutoTokenizer.from_pretrained(repo_or_path, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    repo_or_path,
+    torch_dtype="bfloat16",
+)
+```
+
+## Local Files Included
+
+- `config.json`
+- `generation_config.json`
+- `tekken.json`
+- `model-00001-of-00021.safetensors` ... `model-00021-of-00021.safetensors`
+- `model.safetensors.index.json`
+
+## Citation
+
+If you use this model, please cite this repository:
+
+- https://github.com/ai-twinkle/twinkle-sqlcoder

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 32768,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 11,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 11,
+  "transformers_version": "5.3.0"
+}

model-00001-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3ab1d6679fa15f253efb52881c400a29869f227697e3c938854515a3a9bfbd
+size 4991222816

model-00002-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be0d7dc056befd0c8ef4274a1c68d600c7b3958cc91d47ab271ffa972c8a8f5f
+size 4571793352

model-00003-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ed21cf97b46876d7d5ca52d54f3d37e05475399bea5abb78607d94e79e2bfb
+size 4445963880

model-00004-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac843deca247dac073e2779fff3c5d5624d5f2894195e4690e1a7938ccc2e2f5
+size 4445963880

model-00005-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506bad528c7ccea2ae57838b17f8e2c9a2dd1437f4379955c6cacd620ff502b6
+size 4445963880

model-00006-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254babd7c02b45d28103a76a2c17d4541d0cb613868e0578f6e9ba4b5b2484d8
+size 4445963888

model-00007-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25829b1c2f97e9f73dc59edbbab6601012d8bf817e5aeb2bbf92b20a338c896f
+size 4445963896

model-00008-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7993aa1afc0b6089d821086459bf4f14079e5b175e7182ef49c2899da1cb384
+size 4445963896

model-00009-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936fe43a9bc895cca7fc9b4b8e37aaf0ed734be0a46e5317ef1382066b9c84f8
+size 4445963896

model-00010-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1384dcddb76f0dc53ba283cdd0374d8190692919e11d0052c406ba3b31929eff
+size 4445963896

model-00011-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b7e7d9c5bb9e06d682348ccef814d1f66847f2c11048e8215765c1df213a17
+size 4445963896

model-00012-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19fb55daa2be72b227ddfd6154f81f6a6a3e466e34b4149de624c63364a382d
+size 4445963896

model-00013-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc19f59a40fd61fd270dbe55672362cf231ab0443c1b1bffaa161690d10c8c3
+size 4445963896

model-00014-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2e8eb3e6d2c78922f22e9e04b287dc5b633c154162fec7a43d5875cdf58e9b
+size 4445963896

model-00015-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b648d8ed956c9d5b455918915aef8310146300d55026be5d9b53de98fb08a279
+size 4445963896

model-00016-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e868cfa8b7ed9a85f3482c75f0a410db8aa3ebbc4251b0a0c24976581c9cb8
+size 4445963896

model-00017-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:280c2a402b8b0c160ef4910a88a20c62e1ffbd05c0ab700df4955405d5f693ab
+size 4445963896

model-00018-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c95a45450e3a67b41aa0ef2f8777d84a310e1a73bc8a2488f4399cc121e48f8
+size 4445963896

model-00019-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1984f7c420b66c1fd3cf0ed9fe53ec5d68e00f248b0f6a010b0d085084731ec
+size 4445963896

model-00020-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11ffb54f3933c17b22a6babfff96afac85e0af1c2f925451bd4de90c77b4edf5
+size 4445963896

model-00021-of-00021.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a27f4f32007eb1c604fc4eb5e711a623900298facef60f526a9e3dc4798158b
+size 4699289144

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 94289612800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00021-of-00021.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00021.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00021.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00021.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00021.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00021.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00021.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00021.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00021.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00021.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00015-of-00021.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00021.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00016-of-00021.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00017-of-00021.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00018-of-00021.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00019-of-00021.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00020-of-00021.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00021.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00021.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00021.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00021-of-00021.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00021.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00021.safetensors",
+    "model.norm.weight": "model-00021-of-00021.safetensors"
+  }
+}

tekken.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4b90a968dbc67ef3975129d0b78a2e3cbb6bea340ab9205f22e8a0308b1ffc5
+size 14801223