Upload folder using huggingface_hub (#1)

- b60b5ac5d6d2fa9f39a4467fc3c069e39a215adb9fada8c1901cdc9a1bd3a7f0 (20835c125e0336f358f521db392752d714aee9fc)
- 5a579870a649908050fe5d01c10d33cfcb11bcb6b564ebffbdc2fb4ff51dd7f0 (acc6917363be5a52cc86d9d5e18eb634ff705959)
- 25e15b6f2699e2c6eb2c37a8d252d2edf6b6784836a29c7405d1a630f74ebac8 (34da95dc299c611878350a22a7ba123ba25cbbd7)
- 4708a328725a2f78b4f707f2fc5ecca33a9af8f74291c1f4955e851549d3c3df (e455711eee17187fdbdde40b2f3c5beb2e7f330a)
- 950768bcef8bb176bd52e3aede56624ff7f8d8894d40b0c13ed9518288625d08 (55eb826efdade6fe1bbcb27d7ece2593627b5e1a)
- 33d62861be754020df77b2e5d045690dc54133eee94bdea841efe921383a2fc2 (9e3e11ee9db8425cdeb4bf14bb6d3b4266463f32)

README.md

@@ -0,0 +1,34 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+- axolotl
+- mlx
+base_model: mistralai/Mistral-Nemo-Base-2407
+datasets:
+- cognitivecomputations/Dolphin-2.9
+- teknium/OpenHermes-2.5
+- m-a-p/CodeFeedback-Filtered-Instruction
+- cognitivecomputations/dolphin-coder
+- cognitivecomputations/samantha-data
+- microsoft/orca-math-word-problems-200k
+- Locutusque/function-calling-chatml
+- internlm/Agent-FLAN
+---
+
+# mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16
+
+The Model [mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16](https://huggingface.co/mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16) was converted to MLX format from [cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b](https://huggingface.co/cognitivecomputations/dolphin-2.9.3-mistral-nemo-12b) using mlx-lm version **0.16.1**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Dolphin-2.9.3-mistral-nemo-12b-bf16")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 131072,
+  "<|im_start|>": 131073
+}

config.json

@@ -0,0 +1,26 @@
+{
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 131072,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 1024000,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.43.0.dev0",
+    "use_cache": false,
+    "vocab_size": 131074
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e14454befc049d9b63776cddf0671b06c3bd4eea4802a42b69f85b9292196b6
+size 5264023216

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1574bd1e87e87bb05fa63d0bac5224d0e1561f6bbebaeca241353a079304bb4
+size 5347952415

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa70c9c611bd9a92586b2e4f097d8ce66ef34864b24232f748b464af226833a
+size 5305989047

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9090b0715ce46d3461288ce9b5d4f5caf66a4426c6c15727a3ac56671a98219b
+size 5306009758

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc8aa8ab94bad14f9be95b086c4286e529a0b72d8cc453bc420bc7bf8766c567
+size 3271673594

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+    "metadata": {
+        "total_size": 24495605760
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00005-of-00005.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+        "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+        "model.norm.weight": "model-00005-of-00005.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}