Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+---
+license: other
+license_name: deepseek
+license_link: LICENSE
+tags:
+- mlx
+base_model: deepseek-ai/deepseek-coder-33b-instruct
+---
+
+# sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit
+
+The Model [sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit](https://huggingface.co/sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit) was converted to MLX format from [deepseek-ai/deepseek-coder-33b-instruct](https://huggingface.co/deepseek-ai/deepseek-coder-33b-instruct) using mlx-lm version **0.31.2**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("sleepy186247/deepseek-coder-33b-instruct-mlx-4Bit")
+
+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)
+```

chat_template.jinja

@@ -0,0 +1,26 @@
+{% if not add_generation_prompt is defined %}
+{% set add_generation_prompt = false %}
+{% endif %}
+{%- set ns = namespace(found=false) -%}
+{%- for message in messages -%}
+    {%- if message['role'] == 'system' -%}
+        {%- set ns.found = true -%}
+    {%- endif -%}
+{%- endfor -%}
+{{bos_token}}{%- if not ns.found -%}
+{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\n'}}
+{%- endif %}
+{%- for message in messages %}
+    {%- if message['role'] == 'system' %}
+{{ message['content'] }}
+    {%- else %}
+        {%- if message['role'] == 'user' %}
+{{'### Instruction:\n' + message['content'] + '\n'}}
+        {%- else %}
+{{'### Response:\n' + message['content'] + '\n<|EOT|>\n'}}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{% if add_generation_prompt %}
+{{'### Response:'}}
+{% endif %}

config.json

@@ -0,0 +1,38 @@
+{
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 32013,
+    "eos_token_id": 32021,
+    "hidden_act": "silu",
+    "hidden_size": 7168,
+    "initializer_range": 0.02,
+    "intermediate_size": 19200,
+    "max_position_embeddings": 16384,
+    "model_type": "llama",
+    "num_attention_heads": 56,
+    "num_hidden_layers": 62,
+    "num_key_value_heads": 8,
+    "pretraining_tp": 1,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 4,
+        "mode": "affine"
+    },
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+        "factor": 4.0,
+        "type": "linear"
+    },
+    "rope_theta": 100000,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.33.1",
+    "use_cache": true,
+    "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32021,
+  "transformers_version": "4.34.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5936e469def9ef6b3a23be68ce8be51c42a35c62bef8618fbbae85956c985ab
+size 5345224438

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67330ad8ba405aee5d954d9b980c487f338d15f483ca0dd78db851af768d9157
+size 5365725669

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce6aab5ad7bbfe08f4356e05a2ae3f593b5dd873c696710fba21c8542d567d7
+size 5365725651

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c79dc6da7694f3ce0e34784b1f66d487726d10e0eba207d9f4c14e5fcb58972
+size 2680209536

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|EOT|>",
+  "is_local": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}