pushing cuda mlc no sharding

README.md

@@ -0,0 +1,53 @@
+---
+license: llama2
+datasets:
+- glaiveai/glaive-code-assistant
+language:
+- en
+tags:
+- code
+---
+
+# Glaive-coder-7b
+
+Glaive-coder-7b is a 7B parameter code model trained on a dataset of ~140k programming related problems and solutions generated from Glaive’s synthetic data generation platform.
+
+The model is fine-tuned on the CodeLlama-7b model.
+
+## Usage:
+
+The model is trained to act as a code assistant, and can do both single instruction following and multi-turn conversations.
+It follows the same prompt format as CodeLlama-7b-Instruct-
+```
+<s>[INST]
+<<SYS>>
+{{ system_prompt }}
+<</SYS>>
+
+{{ user_msg }} [/INST] {{ model_answer }} </s>
+<s>[INST] {{ user_msg }} [/INST]
+```
+
+You can run the model in the following way-
+
+```python
+from transformers import AutoModelForCausalLM , AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("glaiveai/glaive-coder-7b")
+model = AutoModelForCausalLM.from_pretrained("glaiveai/glaive-coder-7b").half().cuda()
+
+def fmt_prompt(prompt):
+    return f"<s> [INST] {prompt} [/INST]"
+
+inputs = tokenizer(fmt_prompt(prompt),return_tensors="pt").to(model.device)
+
+outputs = model.generate(**inputs,do_sample=True,temperature=0.1,top_p=0.95,max_new_tokens=100)
+
+print(tokenizer.decode(outputs[0],skip_special_tokens=True,clean_up_tokenization_spaces=False))
+```
+
+## Benchmarks:
+
+The model achieves a 63.1% pass@1 on HumanEval and a 45.2% pass@1 on MBPP, however it is evident that these benchmarks are not representative of real-world usage of code models so we are launching the [Code Models Arena](https://arena.glaive.ai/) to let users vote on model outputs so we can have a better understanding of user preference on code models and come up with new and better benchmarks. We plan to release the Arena results as soon as we have a sufficient amount of data.
+
+Join the Glaive [discord](https://discord.gg/fjQ4uf3yWD) for improvement suggestions, bug-reports and collaborating on more open-source projects.

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|pad|>": 32016
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "max_seq_len": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.0",
+  "use_cache": true,
+  "vocab_size": 32017
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.32.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4c35e92e96e3493907fb7e52af0638176ee92dd1067c64d3081ed2a0f19972d
+size 26954367285

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|pad|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 4096,
+  "pad_token": null,
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "trust_remote_code": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_fast": false
+}