Add files using upload-large-folder tool

README.md

@@ -2,35 +2,7 @@
 license: mit
 pipeline_tag: text-generation
 library_name: mlx
+base_model: moonshotai/Kimi-Linear-48B-A3B-Instruct
 tags:
 - mlx
-base_model: moonshotai/Kimi-Linear-48B-A3B-Instruct
 ---
-
-# mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit
-
-This model [mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit](https://huggingface.co/mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit) was
-converted to MLX format from [moonshotai/Kimi-Linear-48B-A3B-Instruct](https://huggingface.co/moonshotai/Kimi-Linear-48B-A3B-Instruct)
-using mlx-lm version **0.28.4**.
-
-## Use with mlx
-
-```bash
-pip install mlx-lm
-```
-
-```python
-from mlx_lm import load, generate
-
-model, tokenizer = load("mlx-community/Kimi-Linear-48B-A3B-Instruct-4bit")
-
-prompt = "hello"
-
-if tokenizer.chat_template is not None:
-    messages = [{"role": "user", "content": prompt}]
-    prompt = tokenizer.apply_chat_template(
-        messages, add_generation_prompt=True
-    )
-
-response = generate(model, tokenizer, prompt=prompt, verbose=True)
-```

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db38fb201a191ad063c8bece9199d5e0593a7298340a45e39c0a515ca4139436
-size 5151587695
+oid sha256:c2e67b2c1b431e78a2331b837bb75b8c0e3cd80566379feb255a3663adb0f1e7
+size 5151587757

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e45e43fed1e23edb5be8417f06f826aab38a96161242f6e5c5272cb14ba530a
-size 5224824450
+oid sha256:d4f05018a6aec2ea12eb3866e3d31ba8477faca1396e18246f9581fffc7649f3
+size 5224824506

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0155ad2d550706dd18050bc7c63b97eb7cedc2b29c7451a69ec633e4c62996e
-size 5218888436
+oid sha256:f3724036209b2b49d4d9cbdd1d2f5e0702d8626441ac6c343144ee76deee9e2b
+size 5218888514

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd28bc5d3165c4598115568293081a80cee52b76b1bbaf733fcc58d419db4849
-size 5224824667
+oid sha256:f5170b87ec6456eec97104487bef4f5129f3ba13157b7c0cdd5c3f06fd3f79bb
+size 5224824723

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4660721f9930c20406d9528ccf968c23fb9c8a99808eee03f8f45091dd270dbe
-size 5224824647
+oid sha256:43428e7d22d9dde1377d0eee2544be9ed3a6a439cf27b2f3e5385b7baff450a1
+size 5224824701

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b6489961897e93b8e5696946ac5b07eb5cf0d5b7b2881b037a120dcd4f8e1b
-size 1596289056
+oid sha256:e36748ad3261fc25b54c34e384785d183fe61bd9603197d4e5097af2dd3546ee
+size 1596289084

model.safetensors.index.json

@@ -192,10 +192,10 @@
         "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
         "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.11.self_attn.kv_a_norm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.11.self_attn.kv_a_proj.biases": "model-00003-of-00006.safetensors",
-        "model.layers.11.self_attn.kv_a_proj.scales": "model-00003-of-00006.safetensors",
-        "model.layers.11.self_attn.kv_a_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00006.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00006.safetensors",
+        "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00006.safetensors",
         "model.layers.11.self_attn.kv_b_proj.biases": "model-00003-of-00006.safetensors",
         "model.layers.11.self_attn.kv_b_proj.scales": "model-00003-of-00006.safetensors",
         "model.layers.11.self_attn.kv_b_proj.weight": "model-00003-of-00006.safetensors",
@@ -400,10 +400,10 @@
         "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00003-of-00006.safetensors",
         "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00003-of-00006.safetensors",
         "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.15.self_attn.kv_a_norm.weight": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.kv_a_proj.biases": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.kv_a_proj.scales": "model-00003-of-00006.safetensors",
-        "model.layers.15.self_attn.kv_a_proj.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00003-of-00006.safetensors",
+        "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00006.safetensors",
         "model.layers.15.self_attn.kv_b_proj.biases": "model-00003-of-00006.safetensors",
         "model.layers.15.self_attn.kv_b_proj.scales": "model-00003-of-00006.safetensors",
         "model.layers.15.self_attn.kv_b_proj.weight": "model-00003-of-00006.safetensors",
@@ -608,10 +608,10 @@
         "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00004-of-00006.safetensors",
         "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00004-of-00006.safetensors",
         "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.kv_a_norm.weight": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.kv_a_proj.biases": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.kv_a_proj.scales": "model-00004-of-00006.safetensors",
-        "model.layers.19.self_attn.kv_a_proj.weight": "model-00004-of-00006.safetensors",
+        "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00004-of-00006.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00004-of-00006.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00004-of-00006.safetensors",
+        "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00006.safetensors",
         "model.layers.19.self_attn.kv_b_proj.biases": "model-00004-of-00006.safetensors",
         "model.layers.19.self_attn.kv_b_proj.scales": "model-00004-of-00006.safetensors",
         "model.layers.19.self_attn.kv_b_proj.weight": "model-00004-of-00006.safetensors",
@@ -873,10 +873,10 @@
         "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00005-of-00006.safetensors",
         "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00005-of-00006.safetensors",
         "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.23.self_attn.kv_a_norm.weight": "model-00005-of-00006.safetensors",
-        "model.layers.23.self_attn.kv_a_proj.biases": "model-00005-of-00006.safetensors",
-        "model.layers.23.self_attn.kv_a_proj.scales": "model-00005-of-00006.safetensors",
-        "model.layers.23.self_attn.kv_a_proj.weight": "model-00005-of-00006.safetensors",
+        "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00005-of-00006.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00005-of-00006.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00005-of-00006.safetensors",
+        "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00006.safetensors",
         "model.layers.23.self_attn.kv_b_proj.biases": "model-00005-of-00006.safetensors",
         "model.layers.23.self_attn.kv_b_proj.scales": "model-00005-of-00006.safetensors",
         "model.layers.23.self_attn.kv_b_proj.weight": "model-00005-of-00006.safetensors",
@@ -1024,10 +1024,10 @@
         "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00006-of-00006.safetensors",
         "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00006-of-00006.safetensors",
         "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.26.self_attn.kv_a_norm.weight": "model-00006-of-00006.safetensors",
-        "model.layers.26.self_attn.kv_a_proj.biases": "model-00006-of-00006.safetensors",
-        "model.layers.26.self_attn.kv_a_proj.scales": "model-00006-of-00006.safetensors",
-        "model.layers.26.self_attn.kv_a_proj.weight": "model-00006-of-00006.safetensors",
+        "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00006-of-00006.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00006.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00006.safetensors",
+        "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00006.safetensors",
         "model.layers.26.self_attn.kv_b_proj.biases": "model-00006-of-00006.safetensors",
         "model.layers.26.self_attn.kv_b_proj.scales": "model-00006-of-00006.safetensors",
         "model.layers.26.self_attn.kv_b_proj.weight": "model-00006-of-00006.safetensors",
@@ -1061,10 +1061,10 @@
         "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00006.safetensors",
         "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00006.safetensors",
         "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.kv_a_norm.weight": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.kv_a_proj.biases": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.kv_a_proj.scales": "model-00001-of-00006.safetensors",
-        "model.layers.3.self_attn.kv_a_proj.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00006.safetensors",
+        "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00006.safetensors",
         "model.layers.3.self_attn.kv_b_proj.biases": "model-00001-of-00006.safetensors",
         "model.layers.3.self_attn.kv_b_proj.scales": "model-00001-of-00006.safetensors",
         "model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-00006.safetensors",
@@ -1269,10 +1269,10 @@
         "model.layers.7.mlp.switch_mlp.up_proj.scales": "model-00002-of-00006.safetensors",
         "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00002-of-00006.safetensors",
         "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.kv_a_norm.weight": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.kv_a_proj.biases": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.kv_a_proj.scales": "model-00002-of-00006.safetensors",
-        "model.layers.7.self_attn.kv_a_proj.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.biases": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.scales": "model-00002-of-00006.safetensors",
+        "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00006.safetensors",
         "model.layers.7.self_attn.kv_b_proj.biases": "model-00002-of-00006.safetensors",
         "model.layers.7.self_attn.kv_b_proj.scales": "model-00002-of-00006.safetensors",
         "model.layers.7.self_attn.kv_b_proj.weight": "model-00002-of-00006.safetensors",