add cuda_int4 files
Browse files- cuda_int4/chat_template.jinja +93 -0
- cuda_int4/genai_config.json +56 -0
- cuda_int4/model.onnx +3 -0
- cuda_int4/model.onnx.data +3 -0
- cuda_int4/special_tokens_map.json +19 -0
- cuda_int4/tokenizer.json +3 -0
- cuda_int4/tokenizer_config.json +0 -0
cuda_int4/chat_template.jinja
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token }}
|
| 2 |
+
{%- if custom_tools is defined %}
|
| 3 |
+
{%- set tools = custom_tools %}
|
| 4 |
+
{%- endif %}
|
| 5 |
+
{%- if not tools_in_user_message is defined %}
|
| 6 |
+
{%- set tools_in_user_message = true %}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{%- if not date_string is defined %}
|
| 9 |
+
{%- if strftime_now is defined %}
|
| 10 |
+
{%- set date_string = strftime_now("%d %b %Y") %}
|
| 11 |
+
{%- else %}
|
| 12 |
+
{%- set date_string = "26 Jul 2024" %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if not tools is defined %}
|
| 16 |
+
{%- set tools = none %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
|
| 19 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
| 20 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 21 |
+
{%- set system_message = messages[0]['content']|trim %}
|
| 22 |
+
{%- set messages = messages[1:] %}
|
| 23 |
+
{%- else %}
|
| 24 |
+
{%- set system_message = "" %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
|
| 27 |
+
{#- System message #}
|
| 28 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
| 29 |
+
{%- if tools is not none %}
|
| 30 |
+
{{- "Environment: ipython\n" }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
| 33 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
| 34 |
+
{%- if tools is not none and not tools_in_user_message %}
|
| 35 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
| 36 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 37 |
+
{{- "Do not use variables.\n\n" }}
|
| 38 |
+
{%- for t in tools %}
|
| 39 |
+
{{- t | tojson(indent=4) }}
|
| 40 |
+
{{- "\n\n" }}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- system_message }}
|
| 44 |
+
{{- "<|eot_id|>" }}
|
| 45 |
+
|
| 46 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
| 47 |
+
{%- if tools_in_user_message and not tools is none %}
|
| 48 |
+
{#- Extract the first user message so we can plug it in here #}
|
| 49 |
+
{%- if messages | length != 0 %}
|
| 50 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
| 51 |
+
{%- set messages = messages[1:] %}
|
| 52 |
+
{%- else %}
|
| 53 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
| 56 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
| 57 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
| 58 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 59 |
+
{{- "Do not use variables.\n\n" }}
|
| 60 |
+
{%- for t in tools %}
|
| 61 |
+
{{- t | tojson(indent=4) }}
|
| 62 |
+
{{- "\n\n" }}
|
| 63 |
+
{%- endfor %}
|
| 64 |
+
{{- first_user_message + "<|eot_id|>"}}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
|
| 67 |
+
{%- for message in messages %}
|
| 68 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
| 69 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
| 70 |
+
{%- elif 'tool_calls' in message %}
|
| 71 |
+
{%- if not message.tool_calls|length == 1 %}
|
| 72 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 76 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
| 77 |
+
{{- '"parameters": ' }}
|
| 78 |
+
{{- tool_call.arguments | tojson }}
|
| 79 |
+
{{- "}" }}
|
| 80 |
+
{{- "<|eot_id|>" }}
|
| 81 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
| 82 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
| 83 |
+
{%- if message.content is mapping or message.content is iterable %}
|
| 84 |
+
{{- message.content | tojson }}
|
| 85 |
+
{%- else %}
|
| 86 |
+
{{- message.content }}
|
| 87 |
+
{%- endif %}
|
| 88 |
+
{{- "<|eot_id|>" }}
|
| 89 |
+
{%- endif %}
|
| 90 |
+
{%- endfor %}
|
| 91 |
+
{%- if add_generation_prompt %}
|
| 92 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 93 |
+
{%- endif %}
|
cuda_int4/genai_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model": {
|
| 3 |
+
"bos_token_id": 128000,
|
| 4 |
+
"context_length": 131072,
|
| 5 |
+
"decoder": {
|
| 6 |
+
"session_options": {
|
| 7 |
+
"log_id": "onnxruntime-genai",
|
| 8 |
+
"provider_options": [
|
| 9 |
+
{
|
| 10 |
+
"cuda": {
|
| 11 |
+
"enable_cuda_graph": "0",
|
| 12 |
+
"enable_skip_layer_norm_strict_mode": "1"
|
| 13 |
+
}
|
| 14 |
+
}
|
| 15 |
+
]
|
| 16 |
+
},
|
| 17 |
+
"filename": "model.onnx",
|
| 18 |
+
"head_size": 128,
|
| 19 |
+
"hidden_size": 3072,
|
| 20 |
+
"inputs": {
|
| 21 |
+
"input_ids": "input_ids",
|
| 22 |
+
"attention_mask": "attention_mask",
|
| 23 |
+
"past_key_names": "past_key_values.%d.key",
|
| 24 |
+
"past_value_names": "past_key_values.%d.value"
|
| 25 |
+
},
|
| 26 |
+
"outputs": {
|
| 27 |
+
"logits": "logits",
|
| 28 |
+
"present_key_names": "present.%d.key",
|
| 29 |
+
"present_value_names": "present.%d.value"
|
| 30 |
+
},
|
| 31 |
+
"num_attention_heads": 24,
|
| 32 |
+
"num_hidden_layers": 28,
|
| 33 |
+
"num_key_value_heads": 8
|
| 34 |
+
},
|
| 35 |
+
"eos_token_id": 128001,
|
| 36 |
+
"pad_token_id": 128001,
|
| 37 |
+
"type": "llama",
|
| 38 |
+
"vocab_size": 156940
|
| 39 |
+
},
|
| 40 |
+
"search": {
|
| 41 |
+
"diversity_penalty": 0.0,
|
| 42 |
+
"do_sample": true,
|
| 43 |
+
"early_stopping": true,
|
| 44 |
+
"length_penalty": 1.0,
|
| 45 |
+
"max_length": 131072,
|
| 46 |
+
"min_length": 0,
|
| 47 |
+
"no_repeat_ngram_size": 0,
|
| 48 |
+
"num_beams": 1,
|
| 49 |
+
"num_return_sequences": 1,
|
| 50 |
+
"past_present_share_buffer": true,
|
| 51 |
+
"repetition_penalty": 1.0,
|
| 52 |
+
"temperature": 0.6,
|
| 53 |
+
"top_k": 1,
|
| 54 |
+
"top_p": 0.9
|
| 55 |
+
}
|
| 56 |
+
}
|
cuda_int4/model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d051bae5c952bf0aaff60d6ffdfdca5769708fd036e8d71d860457fb40797260
|
| 3 |
+
size 209059
|
cuda_int4/model.onnx.data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58446592b65392af30a50c2cd5d4b403abfb6aefad9bd03332e4c2e161b012e5
|
| 3 |
+
size 2854887424
|
cuda_int4/special_tokens_map.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|audio|>"
|
| 4 |
+
],
|
| 5 |
+
"bos_token": {
|
| 6 |
+
"content": "<|begin_of_text|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"content": "<|eot_id|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
}
|
| 19 |
+
}
|
cuda_int4/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc3fecb199b4170636dbfab986d25f628157268d37b861f9cadaca60b1353bce
|
| 3 |
+
size 22849547
|
cuda_int4/tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|