swiftkv llama 8b fp8

.gitattributes

@@ -33,4 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -13,11 +13,6 @@ For more details about SwiftKV and how to use it:
 * 📝 [SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation (arXiv)](https://arxiv.org/abs/2410.03960)
 * 🚀 [Getting started guide](https://github.com/Snowflake-Labs/vllm/tree/swiftkv/examples/swiftkv)
 
-## Revisions
-
-* **release-2508 (Aug 2025):** Updated model weights for long-context up to 128K
-* **release-2412 (Dec 2024):** Initial model release
-
 ## Performance Metrics
 
 To evaluate SwiftKV’s performance, we focus on the following key metrics (see more details in our [blog](https://www.snowflake.com/engineering-blog/swiftkv-llm-compute-reduction/)):

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/data-fast/llama-3.1-swiftkv-8b-instruct-long-prod",
+  "_name_or_path": "/data-fast/swiftkv-8b-prod/",
   "architectures": [
     "LlamaSwiftKVForCausalLM"
   ],
@@ -11,13 +11,12 @@
     128008,
     128009
   ],
-  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "key_value_group_size": 1,
-  "max_position_embeddings": 131072,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama_swiftkv",
   "num_attention_heads": 32,
@@ -59,7 +58,7 @@
       }
     },
     "format": "float-quantized",
-    "global_compression_ratio": 1.5055096792031475,
+    "global_compression_ratio": 2.014836000728121,
     "ignore": [
       "lm_head"
     ],
@@ -78,8 +77,8 @@
   "rope_theta": 500000.0,
   "swiftkv": true,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.0",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,12 +1,10 @@
 {
+  "_from_model_config": true,
   "bos_token_id": 128000,
-  "do_sample": true,
   "eos_token_id": [
     128001,
     128008,
     128009
   ],
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.47.0"
+  "transformers_version": "4.44.2"
 }

model-00001-of-00002.safetensors → model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87c9e82e09fa8aa41719102830c87133e0dbf688b9b3f6532a82339ec59b759
-size 4970031728
+oid sha256:ec250bf8cd44778ec1c652b80f902806c2f1c001eb37497c09f72a109a930857
+size 4981367864

model-00002-of-00002.safetensors → model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d168470bbad2547c15d728ef0fca79dd2d157ac7d89654c9f3988d1556ff6c2b
-size 4516853216
+oid sha256:4726b2f5c7e9f9b40aafd595706a45567da5e3582418b4c79959e6121a569a72
+size 4509004976

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807f447c6cbb2ca067d666792676583d839a732328c5aa624dd9bf26fc00fac4
+size 2101346432

recipe.yaml

@@ -2,5 +2,5 @@ DEFAULT_stage:
   DEFAULT_modifiers:
     QuantizationModifier:
       ignore: [lm_head]
-      targets: [Linear]
+      targets: Linear
       scheme: FP8_DYNAMIC

tokenizer_config.json

@@ -2053,7 +2053,6 @@
   "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|eot_id|>",
-  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"