10bf2ece3fc58a3cbba789fd2962d0f98d86f4d872dea20841b67e49443f932d

README.md

@@ -1,17 +1,17 @@
 ---
+base_model: karakuri-ai/karakuri-lm-8x7b-chat-v0.1
+datasets:
+- OpenAssistant/oasst2
+- nvidia/HelpSteer
 language:
 - en
 - ja
-license: apache-2.0
 library_name: transformers
+license: apache-2.0
 tags:
 - mixtral
 - steerlm
 - mlx
-base_model: tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1
-datasets:
-- OpenAssistant/oasst2
-- nvidia/HelpSteer
 model-index:
 - name: karakuri-ai/karakuri-lm-8x7b-chat-v0.1
   results:
@@ -33,8 +33,9 @@ model-index:
 ---
 
 # mlx-community/karakuri-lm-8x7b-chat-v0.1-8bit
-This model was converted to MLX format from [`karakuri-ai/karakuri-lm-8x7b-chat-v0.1`]() using mlx-lm version **0.12.1**.
-Refer to the [original model card](https://huggingface.co/karakuri-ai/karakuri-lm-8x7b-chat-v0.1) for more details on the model.
+
+The Model [mlx-community/karakuri-lm-8x7b-chat-v0.1-8bit](https://huggingface.co/mlx-community/karakuri-lm-8x7b-chat-v0.1-8bit) was converted to MLX format from [karakuri-ai/karakuri-lm-8x7b-chat-v0.1](https://huggingface.co/karakuri-ai/karakuri-lm-8x7b-chat-v0.1) using mlx-lm version **0.19.0**.
+
 ## Use with mlx
 
 ```bash
@@ -45,5 +46,14 @@ pip install mlx-lm
 from mlx_lm import load, generate
 
 model, tokenizer = load("mlx-community/karakuri-lm-8x7b-chat-v0.1-8bit")
-response = generate(model, tokenizer, prompt="hello", verbose=True)
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
 ```

config.json

@@ -21,6 +21,10 @@
         "group_size": 64,
         "bits": 8
     },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8
+    },
     "rms_norm_eps": 1e-05,
     "rope_theta": 1000000.0,
     "router_aux_loss_coef": 0.02,

tokenizer_config.json

@@ -1,6 +1,7 @@
 {
   "add_bos_token": true,
   "add_eos_token": false,
+  "add_prefix_space": null,
   "added_tokens_decoder": {
     "0": {
       "content": "<unk>",